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. 15-RESID-POST-AA
    6. 27378
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     проведення
    -0.07
     clipping
    -0.06
    ingen
    -0.06
     Rather
    -0.06
     wei
    -0.06
     **)&
    -0.06
    iming
    -0.06
     frags
    -0.06
     ATH
    -0.06
    折
    -0.06
    POSITIVE LOGITS
    _KP
    0.08
     Sk
    0.07
    	pub
    0.07
    .Public
    0.07
     souls
    0.07
    лиз
    0.07
     식
    0.06
     Expression
    0.06
    icopt
    0.06
     keeps
    0.06
    Activations Density 0.042%

    No Known Activations