© 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. 93684
    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
    landers
    -0.08
    ä¿Ĭ
    -0.07
    pla
    -0.07
    oad
    -0.07
    plan
    -0.06
    exampleInput
    -0.06
    ï¿¥
    -0.06
     Pla
    -0.06
    Ïĥμα
    -0.06
    ldb
    -0.06
    POSITIVE LOGITS
    Interpolator
    0.07
    antis
    0.07
     ActionType
    0.07
    letic
    0.07
    âĸį
    0.06
     Brid
    0.06
    quot
    0.06
    ÑĤÑĮ
    0.06
     automát
    0.06
    ort
    0.06
    Activations Density 0.001%

    No Known Activations