© 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. 17-LLAMASCOPE-RES-131K
    6. 106362
    Prev
    Next
    INDEX
    Explanations

    references to specific football players and their attributes

    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
    arness
    -0.08
    вок
    -0.08
    ationToken
    -0.07
     ikt
    -0.07
    tfoot
    -0.07
    Overrides
    -0.07
    éĹ´
    -0.07
    arged
    -0.07
    éĻĦ
    -0.07
    lamaya
    -0.07
    POSITIVE LOGITS
     security
    0.13
     Security
    0.11
    Security
    0.10
    security
    0.09
     defense
    0.09
    -security
    0.09
    /security
    0.08
    ecurity
    0.08
     defence
    0.08
     defensive
    0.08
    Activations Density 0.043%

    No Known Activations