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. 3-RESID-POST-AA
    6. 122344
    Prev
    Next
    INDEX
    Explanations

    str

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repetition
    -0.07
     expense
    -0.07
    -full
    -0.06
     expenses
    -0.06
    675
    -0.06
     постеп
    -0.06
    oti
    -0.06
     платеж
    -0.06
     recognizing
    -0.06
     miracles
    -0.06
    POSITIVE LOGITS
     str
    0.17
    _str
    0.09
     Stra
    0.09
    .str
    0.08
    ,str
    0.08
    	str
    0.07
    Stra
    0.07
    derabad
    0.07
    str
    0.07
    	lbl
    0.07
    Activations Density 0.007%

    No Known Activations