© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55821
    Prev
    Next
    INDEX
    Explanations

    lymph

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of specific lymphoid malignancy names or subtype abbreviations (e.g., MALT, CLL, FL, MCL, NHL).

    oai_token-act-pair · o4-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
     RUS
    -0.07
    Eff
    -0.07
     бог
    -0.07
     Borrow
    -0.06
    (pDX
    -0.06
     độc
    -0.06
    іон
    -0.06
    .SerializedName
    -0.06
    지막
    -0.06
     zvíř
    -0.06
    POSITIVE LOGITS
     chapters
    0.07
     Counties
    0.06
    .ConnectionStrings
    0.06
    -heading
    0.06
     directive
    0.06
    Context
    0.06
     Copyright
    0.06
     comic
    0.06
     banking
    0.06
    .less
    0.06
    Activations Density 0.002%

    No Known Activations