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. 110028
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash

    This neuron fires on the substitution paths in Apache RewriteRule directives (i.e. the “/target”… part and related flags like index.html, $1, etc.).

    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
     receiver
    -0.07
     liter
    -0.06
     neighbor
    -0.06
     Receiver
    -0.06
     Harbor
    -0.06
     persons
    -0.06
     situations
    -0.06
     adversary
    -0.06
     Jaune
    -0.06
     receptive
    -0.06
    POSITIVE LOGITS
    _con
    0.07
    addAction
    0.07
     लगत
    0.07
     плав
    0.06
    ')}>↵
    0.06
    olleyError
    0.06
     bozuk
    0.06
     إد
    0.06
     koş
    0.06
    vla
    0.06
    Activations Density 0.002%

    No Known Activations