© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84435
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related references to identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mw
    -0.06
    @(
    -0.06
    á»
    -0.06
    OLON
    -0.06
    à¹Ĥรà¸ĩà¹ģรม
    -0.06
    ÙĥÙĨ
    -0.06
     mimo
    -0.06
    //{{
    -0.06
    arsers
    -0.06
    _ud
    -0.06
    POSITIVE LOGITS
     aim
    0.12
    oret
    0.11
     goal
    0.10
    goal
    0.08
     focus
    0.08
    agine
    0.08
    缮
    0.08
    yonel
    0.07
     attempt
    0.07
     next
    0.07
    Activations Density 0.054%

    No Known Activations