© 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. 15-LLAMASCOPE-RES-131K
    11. 27179
    Prev
    Next
    INDEX
    Explanations

    terms associated with quality and improvement 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
    836
    -0.06
    atoi
    -0.06
    ithe
    -0.06
    urge
    -0.06
    PMC
    -0.06
     Squ
    -0.06
     Vil
    -0.06
    ikki
    -0.06
    upa
    -0.06
    _UNUSED
    -0.06
    POSITIVE LOGITS
    ibilit
    0.07
    endi
    0.07
    dül
    0.06
    onyms
    0.06
    GLE
    0.06
    tracked
    0.06
    fone
    0.06
     Bri
    0.06
    onto
    0.06
    herited
    0.06
    Activations Density 0.005%

    No Known Activations