© 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
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 102558
    Prev
    Next
    INDEX
    Explanations

    Cambodia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assertThat
    -0.07
    .fixture
    -0.07
    Song
    -0.06
    (Column
    -0.06
     Games
    -0.06
    (/[
    -0.06
    .assertThat
    -0.06
     boasts
    -0.06
    _clock
    -0.06
    	assertThat
    -0.06
    POSITIVE LOGITS
    .red
    0.07
     missionaries
    0.07
    кому
    0.07
     maxY
    0.06
     breakpoint
    0.06
    천
    0.06
    빠
    0.06
     radioactive
    0.06
     �
    0.06
    _RECT
    0.06
    Activations Density 0.003%

    No Known Activations