© 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. 15-LLAMASCOPE-RES-131K
    6. 104053
    Prev
    Next
    INDEX
    Explanations

    the term "black" in various contexts and references

    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
    illard
    -0.08
    cean
    -0.08
    acle
    -0.07
    osa
    -0.07
    phere
    -0.07
    ential
    -0.07
    ekt
    -0.07
    getManager
    -0.07
    osaic
    -0.07
    ulong
    -0.07
    POSITIVE LOGITS
    ened
    0.13
    ness
    0.12
    ening
    0.10
    listed
    0.10
    smith
    0.09
    roads
    0.08
    rd
    0.08
    fish
    0.07
    -quarters
    0.07
    woods
    0.07
    Activations Density 0.026%

    No Known Activations