© 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. 15-LLAMASCOPE-RES-131K
    11. 90131
    Prev
    Next
    INDEX
    Explanations

    occurrences of the symbol used for navigation or categorization in a document

    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
    ocities
    -0.07
    inge
    -0.07
    nick
    -0.07
    udes
    -0.07
    è©
    -0.07
    ĵåIJį
    -0.07
    edo
    -0.06
    antz
    -0.06
    _pan
    -0.06
    orre
    -0.06
    POSITIVE LOGITS
    ziel
    0.06
    ecut
    0.06
     unc
    0.06
    IRT
    0.06
    iti
    0.06
    throp
    0.06
     Fel
    0.06
     Flat
    0.06
     civil
    0.06
     AB
    0.06
    Activations Density 0.001%

    No Known Activations