© 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. 40332
    Prev
    Next
    INDEX
    Explanations

    references to books and literature selection processes

    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
    esz
    -0.06
    .scalablytyped
    -0.06
    toy
    -0.06
    ashboard
    -0.06
     CONTRIBUTORS
    -0.06
     Bottle
    -0.06
    ewire
    -0.05
     Lore
    -0.05
    /render
    -0.05
    æķĻ
    -0.05
    POSITIVE LOGITS
     reading
    0.10
     Reading
    0.10
    Reading
    0.09
    _reading
    0.08
    reading
    0.08
    chap
    0.08
     Pride
    0.07
    READING
    0.07
     اÙĦÙĤر
    0.07
    aris
    0.07
    Activations Density 0.013%

    No Known Activations