© 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. 7-RESID-POST-AA
    6. 36039
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash

    Whether the text is addressing the reader or giving instructions/advice (direct second-person or imperative phrasing).

    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
    449
    -0.07
    anon
    -0.07
    .Ticks
    -0.07
    ertain
    -0.06
    /ge
    -0.06
    columns
    -0.06
    ulist
    -0.06
    .rabbit
    -0.06
    itr
    -0.06
    _un
    -0.06
    POSITIVE LOGITS
    ůvodu
    0.07
     øns
    0.07
     slew
    0.07
    (new
    0.07
     collective
    0.06
     newInstance
    0.06
     علیه
    0.06
    Ups
    0.06
     Translator
    0.06
     defeating
    0.06
    Activations Density 1.130%

    No Known Activations