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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 121019
    Prev
    Next
    INDEX
    Explanations

    Code and data serialization

    np_max-act · gemini-2.0-flash

    the boundaries and markers of markup/code blocks (e.g., XML/HTML tags, prolog "<?xml", CDATA and similar delimiters).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    jon
    -0.06
     Lambda
    -0.06
    693
    -0.06
    online
    -0.06
    _*
    -0.06
    045
    -0.06
    _title
    -0.06
     �
    -0.06
     annum
    -0.06
    вся
    -0.06
    POSITIVE LOGITS
     필요한
    0.07
     المتحدة
    0.07
    arsing
    0.07
    แทน
    0.07
    ическое
    0.06
    .Param
    0.06
     end
    0.06
     Morph
    0.06
    ="";↵
    0.06
     contiguous
    0.06
    Activations Density 0.150%

    No Known Activations