© 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. 11-RESID-POST-AA
    11. 25168
    Prev
    Next
    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash

    The neuron remains completely inactive on all ordinary conversational tokens here, indicating it’s specialized for a pattern not present in these examples.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    top tourist attractions in various cities.

    oai_token-act-pair · gpt-4o-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
     uvád
    -0.07
     canon
    -0.07
     poj
    -0.07
    _SY
    -0.06
     Gonz
    -0.06
     буд
    -0.06
    .StringUtils
    -0.06
     půj
    -0.06
    naissance
    -0.06
    .GraphicsUnit
    -0.06
    POSITIVE LOGITS
     over
    0.10
     Over
    0.09
     OVER
    0.08
     nearing
    0.07
     celebrate
    0.07
    .centerX
    0.07
    違
    0.07
    -over
    0.07
    .bio
    0.06
     surf
    0.06
    Activations Density 0.030%

    No Known Activations