© 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. 9-LLAMASCOPE-RES-131K
    6. 95626
    Prev
    Next
    INDEX
    Explanations

    terms related to trespassing and unlawful entry

    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
    icine
    -0.07
    out
    -0.07
    lems
    -0.07
    ondo
    -0.06
    esta
    -0.06
    .constructor
    -0.06
    aqu
    -0.06
    readcr
    -0.06
    obar
    -0.06
    ouver
    -0.06
    POSITIVE LOGITS
    ses
    0.08
    erville
    0.08
    er
    0.07
    ìĭľìĹIJ
    0.07
     å¸ĥ
    0.07
    752
    0.06
    islav
    0.06
    .sax
    0.06
    AnimationFrame
    0.06
    _excerpt
    0.06
    Activations Density 0.002%

    No Known Activations