© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129021
    Prev
    Next
    INDEX
    Explanations

    symbols or punctuation marks used in structured or formal writing

    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
    ATUS
    -0.09
    blick
    -0.08
    deen
    -0.08
    AREST
    -0.08
    afi
    -0.07
    oba
    -0.07
    HING
    -0.07
    VENTORY
    -0.07
    RIPT
    -0.07
     nhau
    -0.07
    POSITIVE LOGITS
     coll
    0.06
    pill
    0.06
     M
    0.06
    esub
    0.06
    ÑĢоÑģÑĤо
    0.05
     Sty
    0.05
     m
    0.05
     foreground
    0.05
    Âł
    0.05
     mist
    0.05
    Activations Density 0.005%

    No Known Activations