© 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. 84439
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to programming, specifically in service-oriented architectures

    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
    -install
    -0.06
     mamm
    -0.06
    ow
    -0.06
    ois
    -0.06
    oom
    -0.06
     dip
    -0.06
    arend
    -0.06
    pair
    -0.06
    uo
    -0.06
    eral
    -0.05
    POSITIVE LOGITS
    mojom
    0.09
    _generated
    0.08
    _marshall
    0.08
    /Dk
    0.08
    idl
    0.08
    _defs
    0.08
    rena
    0.07
    надлеж
    0.07
    IDL
    0.07
    ascript
    0.07
    Activations Density 0.028%

    No Known Activations