© 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. 119487
    Prev
    Next
    INDEX
    Explanations

    references to processes and frameworks related to organization and management

    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
    Wunused
    -0.07
    رسÛĮ
    -0.07
     ÑĢазви
    -0.06
     Bannon
    -0.06
    umpt
    -0.06
    ernity
    -0.06
    _INF
    -0.06
    .PerformLayout
    -0.06
    agal
    -0.06
     am
    -0.06
    POSITIVE LOGITS
    orst
    0.08
     thereby
    0.07
    oret
    0.07
    atori
    0.07
    ivre
    0.07
    ens
    0.06
    ifar
    0.06
    ekler
    0.06
     Ens
    0.06
     ermög
    0.06
    Activations Density 0.028%

    No Known Activations