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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 125486
    Prev
    Next
    INDEX
    Explanations

    code/file paths

    np_max-act · gemini-2.0-flash

    The neuron is keyed to string literals that look like file or directory paths (i.e. tokens containing slashes and path segments).

    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
     ocur
    -0.07
    Tell
    -0.07
    关系
    -0.06
     charts
    -0.06
    (keys
    -0.06
    Mgr
    -0.06
    伏
    -0.06
     Protocol
    -0.06
     gm
    -0.06
     bore
    -0.06
    POSITIVE LOGITS
     SOS
    0.07
    .coeff
    0.06
    ***↵
    0.06
    RoutingModule
    0.06
     ships
    0.06
     condiciones
    0.06
     села
    0.06
     ragazzi
    0.06
    ⟩
    0.06
     mú
    0.06
    Activations Density 0.090%

    No Known Activations