© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4165
    Prev
    Next
    INDEX
    Explanations

    curly braces and nested structures within code

    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
    (æľ¨
    -0.09
    (æ°´
    -0.08
    unma
    -0.08
    xit
    -0.08
    ÑĥнкÑĤ
    -0.08
    ç¯
    -0.08
    trait
    -0.07
    hra
    -0.07
    (çģ«
    -0.07
    uÃŃ
    -0.07
    POSITIVE LOGITS
     public
    0.12
     friend
    0.11
    friend
    0.10
     friends
    0.10
    public
    0.10
     publicly
    0.09
     protected
    0.08
     FRIEND
    0.07
    protected
    0.07
     friendship
    0.07
    Activations Density 0.007%

    No Known Activations