© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 19381
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    detecting question-like sentence endings (question marks and end-of-utterance/question tokens).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dignity
    -0.07
     paths
    -0.07
    -way
    -0.07
    -zero
    -0.07
    Bind
    -0.07
    datasets
    -0.07
     repositories
    -0.06
    ziehung
    -0.06
     bonds
    -0.06
     histogram
    -0.06
    POSITIVE LOGITS
    厅
    0.07
     unserialize
    0.07
     <+
    0.06
    vp
    0.06
     hast
    0.06
    ้าค
    0.06
     cray
    0.06
    рій
    0.06
    े,
    0.06
    ToLower
    0.06
    Activations Density 0.084%

    No Known Activations