© 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. 78277
    Prev
    Next
    INDEX
    Explanations

    references to constraints and their implications in mathematical formulations

    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
    ChangedEventArgs
    -0.07
    ãĥ³ãĥĦ
    -0.07
    .NotFound
    -0.06
     trÃŃ
    -0.06
     vinden
    -0.06
     Lif
    -0.06
    Scaled
    -0.06
    _mapped
    -0.06
     Chunk
    -0.06
     Vul
    -0.06
    POSITIVE LOGITS
     constraints
    0.15
     constraint
    0.15
     Constraints
    0.13
    constraint
    0.12
    constraints
    0.11
    .constraints
    0.11
     Constraint
    0.11
    Constraint
    0.10
    Constraints
    0.10
    _constraint
    0.10
    Activations Density 0.164%

    No Known Activations