Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 73113
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    z
    -0.07
    (gulp
    -0.07
    }";↵
    -0.07
    _bbox
    -0.07
    ії
    -0.07
     состояния
    -0.06
    ạn
    -0.06
    ]=(
    -0.06
     Pai
    -0.06
    ]],
    -0.06
    POSITIVE LOGITS
     colle
    0.07
     explosives
    0.06
    	NullCheck
    0.06
     ypos
    0.06
    mor
    0.06
    форт
    0.06
    ्मक
    0.06
     편
    0.06
    ังค
    0.06
     خدمت
    0.06
    Activations Density 0.009%

    No Known Activations