© 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. 29694
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries

    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
    ville
    -0.07
     to
    -0.07
    ized
    -0.07
    cker
    -0.07
    arily
    -0.07
    ozor
    -0.07
    ally
    -0.07
     OU
    -0.06
     request
    -0.06
     mild
    -0.06
    POSITIVE LOGITS
    оÑĤÑĮ
    0.07
    solete
    0.07
    .SO
    0.07
     пÑĢо
    0.07
    afort
    0.07
    aland
    0.07
    _trait
    0.06
     iParam
    0.06
    tolua
    0.06
    ORMAT
    0.06
    Activations Density 0.007%

    No Known Activations