Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3521
    Prev
    Next
    INDEX
    Explanations

    entities related to journalism and media organizations

    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
    azzi
    -0.09
    orgen
    -0.08
    #:
    -0.07
    onical
    -0.07
    ilst
    -0.07
    antal
    -0.07
    zl
    -0.07
     ëĺIJíķľ
    -0.07
    ntax
    -0.07
     continu
    -0.06
    POSITIVE LOGITS
     whose
    0.07
    whose
    0.07
    -plus
    0.06
    ako
    0.06
    éĤ£ç§į
    0.06
    ;!
    0.06
    dbcTemplate
    0.06
     (!
    0.05
     Truman
    0.05
    à¥įà¤ł
    0.05
    Activations Density 0.060%

    No Known Activations