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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 53832
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     Tactics
    -0.08
     batt
    -0.07
    แก
    -0.07
    �
    -0.07
     mas
    -0.06
     tactics
    -0.06
    Sea
    -0.06
    ह
    -0.06
    770
    -0.06
    бря
    -0.06
    POSITIVE LOGITS
    [child
    0.06
     budeme
    0.06
    etiyle
    0.06
    .IsDBNull
    0.06
    (#
    0.06
    [Index
    0.06
    Copyright
    0.06
    ALT
    0.06
     إليه
    0.05
    [length
    0.05
    Activations Density 0.007%

    No Known Activations