© 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. 11-RESID-POST-AA
    6. 20850
    Prev
    Next
    INDEX
    Explanations

    signaling

    np_max-act · gemini-2.0-flash

    references to targeted therapies and their implications in cancer treatment.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ten
    -0.07
     그녀
    -0.06
    @endforeach
    -0.06
    .AspNet
    -0.06
    .isdigit
    -0.06
    .COLUMN
    -0.06
    ulle
    -0.06
    �
    -0.06
     پول
    -0.06
    ?>'
    -0.06
    POSITIVE LOGITS
    ancy
    0.07
    cx
    0.07
     previous
    0.07
     inconsistent
    0.07
     border
    0.07
     Tail
    0.06
    ORLD
    0.06
     موارد
    0.06
     tunnel
    0.06
     Rogue
    0.06
    Activations Density 0.010%

    No Known Activations