© 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. 22-LLAMASCOPE-RES-131K
    11. 4058
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas, in various contexts

    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
    zac
    -0.07
    ÄĽtÃŃ
    -0.07
    ouser
    -0.07
    oland
    -0.07
    berger
    -0.07
    imb
    -0.06
    ammad
    -0.06
    andy
    -0.06
    oger
    -0.06
    åde
    -0.06
    POSITIVE LOGITS
    AGES
    0.08
    âĤ
    0.06
    SizePolicy
    0.06
    yc
    0.06
    REET
    0.06
    ages
    0.06
    Street
    0.06
    æ´»
    0.06
    alara
    0.06
    ACING
    0.06
    Activations Density 0.000%

    No Known Activations