© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 120901
    Prev
    Next
    INDEX
    Explanations

    French

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indicates
    -0.06
    ……
    -0.06
     counts
    -0.06
     paramount
    -0.06
    parent
    -0.06
    ----
    -0.06
    แหน
    -0.06
     concentrates
    -0.06
     punish
    -0.06
    .bad
    -0.06
    POSITIVE LOGITS
    络
    0.07
     chú
    0.07
     PyTuple
    0.06
    治疗
    0.06
    Entropy
    0.06
    schools
    0.06
     girişim
    0.06
     Tw
    0.06
    ư�
    0.06
    HeaderInSection
    0.06
    Activations Density 0.000%

    No Known Activations