© 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. 29629
    Prev
    Next
    INDEX
    Explanations

    technical terms and numerical data related to testing and specifications

    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
    _NUM
    -0.08
    esan
    -0.08
    NumberOf
    -0.07
     Num
    -0.07
     num
    -0.07
    Num
    -0.07
    esian
    -0.07
    num
    -0.07
     fleets
    -0.07
     NUM
    -0.07
    POSITIVE LOGITS
     each
    0.10
    each
    0.08
     Each
    0.07
     каждÑĭй
    0.07
    uras
    0.07
    Each
    0.07
    _each
    0.07
     spread
    0.07
    saldo
    0.07
    pread
    0.07
    Activations Density 0.077%

    No Known Activations