© 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. 74832
    Prev
    Next
    INDEX
    Explanations

    numeric patterns and values in data

    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
    olin
    -0.08
    طب
    -0.07
     ffi
    -0.07
     unb
    -0.07
    AGO
    -0.07
    ULO
    -0.07
    unn
    -0.07
    OOK
    -0.07
    PEC
    -0.07
    AKE
    -0.07
    POSITIVE LOGITS
    ica
    0.06
    aks
    0.06
    itespace
    0.06
    770
    0.06
    561
    0.06
    ettes
    0.06
    549
    0.06
    598
    0.06
    460
    0.05
     Edwards
    0.05
    Activations Density 0.001%

    No Known Activations