© 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. 40286
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    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
    žil
    -0.07
    crop
    -0.07
     Std
    -0.07
    BootTest
    -0.07
    }č↵č↵č↵č↵
    -0.06
    ãģĵãĤį
    -0.06
    ichen
    -0.06
    ENSE
    -0.06
    иÑĩа
    -0.06
    folio
    -0.06
    POSITIVE LOGITS
    anch
    0.06
    adio
    0.06
    Cancellation
    0.06
    aclass
    0.06
    âĸº
    0.06
     woodworking
    0.06
    _xor
    0.06
     rez
    0.06
    FileType
    0.06
    оÑģк
    0.06
    Activations Density 0.000%

    No Known Activations