© 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. 5-LLAMASCOPE-RES-131K
    11. 126400
    Prev
    Next
    INDEX
    Explanations

    elements related to document structure and formatting

    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
     requestOptions
    -0.07
    mun
    -0.06
    ktop
    -0.06
    545
    -0.06
    lady
    -0.06
    lad
    -0.06
    fly
    -0.06
    ows
    -0.06
    enu
    -0.06
     gig
    -0.06
    POSITIVE LOGITS
    uggage
    0.07
    )arg
    0.07
    stants
    0.06
    boro
    0.06
    ield
    0.06
    اØŃÛĮ
    0.06
    arges
    0.06
    bate
    0.06
    ounder
    0.06
    _CHOICES
    0.06
    Activations Density 0.001%

    No Known Activations