© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 23756
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     from
    -0.09
     at
    -0.08
    	from
    -0.07
     enorm
    -0.07
    !I
    -0.07
    From
    -0.07
     Saturn
    -0.07
    xito
    -0.07
    皮
    -0.07
     complementary
    -0.07
    POSITIVE LOGITS
     fastball
    0.06
    kubectl
    0.06
    (Py
    0.06
    _thr
    0.06
     рів
    0.06
    )="
    0.06
    �
    0.05
     보기
    0.05
    Baş
    0.05
    /p
    0.05
    Activations Density 0.146%

    No Known Activations