© 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. 75362
    Prev
    Next
    INDEX
    Explanations

    references to external sources or links in the text

    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
    каж
    -0.08
    ockey
    -0.08
    idon
    -0.07
    anzi
    -0.07
    cao
    -0.07
    inqu
    -0.07
    geh
    -0.07
    egov
    -0.06
    éĻµ
    -0.06
    ifton
    -0.06
    POSITIVE LOGITS
    ÑıÑĩ
    0.07
    ATTERN
    0.06
     Organizer
    0.05
    iece
    0.05
    ardon
    0.05
    าะ
    0.05
    Blo
    0.05
     cel
    0.05
     ng
    0.05
     Masc
    0.05
    Activations Density 0.001%

    No Known Activations