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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 55253
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    technical terms and jargon related to specific fields, particularly in scientific and mathematical contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects German case‐inflection suffixes (e.g. the “-dem,” “-der,” “-einer,” etc. endings).

    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
     firstly
    -0.07
    	FOR
    -0.06
    �
    -0.06
    来た
    -0.06
     è
    -0.06
    ăr
    -0.06
     Firstly
    -0.06
     Franti
    -0.06
    _dead
    -0.06
     області
    -0.06
    POSITIVE LOGITS
    सत
    0.07
    _keywords
    0.07
    .Warning
    0.07
     volume
    0.07
     SENT
    0.07
     Cmd
    0.07
    /callback
    0.07
    ackle
    0.06
    (batch
    0.06
     bowls
    0.06
    Activations Density 0.000%

    No Known Activations