© 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. 94128
    Prev
    Next
    INDEX
    Explanations

    references to files and file handling operations

    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
    ran
    -0.08
    rap
    -0.07
    ry
    -0.07
    ãģĬãĤĬ
    -0.07
    land
    -0.07
    ragon
    -0.07
    ÑĢан
    -0.07
    alla
    -0.07
    fall
    -0.07
    ist
    -0.07
    POSITIVE LOGITS
    ëŁ
    0.12
    å¤
    0.11
    :///
    0.11
    aments
    0.08
    holder
    0.08
    system
    0.07
    itoris
    0.07
    Ù쨩
    0.07
    handle
    0.07
    handles
    0.07
    Activations Density 0.036%

    No Known Activations