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. 109572
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing floating‐point numbers (i.e. decimal values).

    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
    inus
    -0.06
    anic
    -0.06
    invoke
    -0.05
     Reads
    -0.05
    _VEC
    -0.05
     punish
    -0.05
    ]init
    -0.05
     заг
    -0.05
    」と
    -0.05
    ;↵
    -0.05
    POSITIVE LOGITS
     ситуа
    0.08
    heiro
    0.07
     petty
    0.07
    _literal
    0.07
     sembl
    0.07
     designers
    0.07
    (sequence
    0.07
     designer
    0.07
     hammer
    0.07
     reserved
    0.07
    Activations Density 0.040%

    No Known Activations