© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77334
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash

    scientific terms related to oral health and its physiological effects.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _ARROW
    -0.06
    teacher
    -0.06
    edited
    -0.06
    pok
    -0.06
    urt
    -0.06
    âng
    -0.06
     enthusiast
    -0.06
     soccer
    -0.05
    Lesson
    -0.05
    OLD
    -0.05
    POSITIVE LOGITS
    .toCharArray
    0.08
    (lbl
    0.07
     yıllık
    0.07
     sketch
    0.07
    >equals
    0.07
    ливо
    0.07
    CppTypeDefinition
    0.06
    mızı
    0.06
     easing
    0.06
     руб
    0.06
    Activations Density 0.030%

    No Known Activations