© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125985
    Prev
    Next
    INDEX
    Explanations

    science fiction references

    np_max-act · gemini-2.0-flash

    references to the number 42 as the supposed answer to existential questions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects and highlights the special header‐ID metadata tokens and adjacent system/assistant message markers in the transcript.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etadata
    -0.07
     Voor
    -0.06
     nhiễ
    -0.06
    Toronto
    -0.06
    .EventArgs
    -0.06
    .ast
    -0.06
     VP
    -0.06
     realms
    -0.06
     siblings
    -0.06
    kdir
    -0.06
    POSITIVE LOGITS
     transpose
    0.07
     ieee
    0.06
     ↵        ↵
    0.06
    沒
    0.06
     赤
    0.06
     مشخص
    0.06
    serir
    0.06
     ).↵↵
    0.06
     useless
    0.06
    Eventually
    0.06
    Activations Density 0.007%

    No Known Activations