© 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. 61866
    Prev
    Next
    INDEX
    Explanations

    keywords related to data analysis or scrutiny

    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
    Ưá»
    -0.07
    /stats
    -0.06
    ModifiedDate
    -0.06
    гов
    -0.06
    canf
    -0.06
    argas
    -0.06
    ãĤ°ãĥ«
    -0.06
    lant
    -0.06
     Gre
    -0.06
    ounder
    -0.06
    POSITIVE LOGITS
     reverse
    0.07
    issen
    0.06
    zheimer
    0.06
     opposite
    0.06
    ¥¿
    0.06
    chn
    0.06
    gether
    0.06
     ramps
    0.06
    ctors
    0.06
    658
    0.06
    Activations Density 0.000%

    No Known Activations