© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77526
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a central or focal position or concept

    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
    .DataAccess
    -0.08
    omu
    -0.08
    gmt
    -0.07
    ëŀĺ
    -0.07
    opot
    -0.07
    aned
    -0.07
    BCM
    -0.06
     McGregor
    -0.06
     fact
    -0.06
    Apr
    -0.06
    POSITIVE LOGITS
     gravity
    0.08
    lations
    0.07
     attention
    0.07
    oje
    0.07
    attention
    0.07
    180
    0.06
     Gravity
    0.06
    focus
    0.06
     TAM
    0.06
    -center
    0.06
    Activations Density 0.012%

    No Known Activations