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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 81351
    Prev
    Next
    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on opening definitional or topic‐setting sentences that introduce and broadly describe a technical concept.

    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
     organisms
    -0.07
    521
    -0.07
     Σα
    -0.06
     weekday
    -0.06
    чива
    -0.06
    isLoading
    -0.06
    leanup
    -0.06
    successfully
    -0.06
    Reset
    -0.06
     deviations
    -0.06
    POSITIVE LOGITS
    "])↵
    0.07
     happening
    0.06
    ])
    ↵
    0.06
     thunder
    0.06
     Saud
    0.06
    _NATIVE
    0.06
     happen
    0.06
    ]).
    0.06
    ])↵↵
    0.06
    ])
    ↵
    ↵
    0.06
    Activations Density 0.075%

    No Known Activations