© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126768
    Prev
    Next
    INDEX
    Explanations

    Radio station call letters

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on uppercase call-sign strings (e.g. “WHOG-FM,” “WPAY,” “CKLC-FM”), i.e. radio station identifiers.

    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
    _maps
    -0.07
    noDB
    -0.06
    Markers
    -0.06
    pcion
    -0.06
     lion
    -0.06
    όγ
    -0.06
    _Ass
    -0.06
    員
    -0.06
     해야
    -0.06
     Irving
    -0.06
    POSITIVE LOGITS
     screws
    0.08
     hå
    0.07
     hukuk
    0.06
    iyordu
    0.06
    ●●●●
    0.06
    -eslint
    0.06
    持续
    0.06
     coming
    0.06
    	xtype
    0.06
    نی
    0.06
    Activations Density 0.004%

    No Known Activations