© 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. 128338
    Prev
    Next
    INDEX
    Explanations

    means

    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
     Sidd
    -0.07
    909
    -0.07
    scheduler
    -0.07
     alc
    -0.06
    708
    -0.06
     stud
    -0.06
    <*
    -0.06
     IList
    -0.06
    917
    -0.06
    莉
    -0.06
    POSITIVE LOGITS
     mean
    0.12
     means
    0.11
     meant
    0.10
     meaning
    0.10
    means
    0.10
     Meaning
    0.09
     Means
    0.09
    Means
    0.08
     Mean
    0.08
    mean
    0.08
    Activations Density 0.047%

    No Known Activations