© 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. 105890
    Prev
    Next
    INDEX
    Explanations

    numerical data related to company metrics and financial statistics

    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
     (
    -0.07
    -0.06
     prefix
    -0.05
    setw
    -0.05
    .RightToLeft
    -0.05
     form
    -0.05
     —
    -0.05
    kal
    -0.05
    latin
    -0.05
     Moto
    -0.05
    POSITIVE LOGITS
    ignon
    0.09
    ç£
    0.08
    oire
    0.08
    TOT
    0.08
    ActionCreators
    0.07
    ëł¹
    0.07
    inke
    0.07
    opoulos
    0.07
    _OVERRIDE
    0.07
    unction
    0.07
    Activations Density 0.003%

    No Known Activations