© 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. 109883
    Prev
    Next
    INDEX
    Explanations

    trivia

    np_max-act · gemini-2.0-flash

    This neuron detects structural boundary markers (like <|start_header_id|>, <|end_header_id|>, <|eot_id|>) and punctuation (especially question marks) that mark turns or segment ends in the text.

    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
    716
    -0.08
    _dict
    -0.07
    cache
    -0.06
    ürn
    -0.06
     STATS
    -0.06
    까지
    -0.06
    chemes
    -0.06
    -metal
    -0.06
    factor
    -0.06
     Lime
    -0.06
    POSITIVE LOGITS
     路
    0.07
    ]
    ↵
    0.07
    .':
    0.07
     GIVEN
    0.06
     развити
    0.06
     ################
    0.06
    °
    0.06
    >(_
    0.06
    '))↵↵
    0.06
     Sản
    0.06
    Activations Density 0.044%

    No Known Activations