© 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. 128646
    Prev
    Next
    INDEX
    Explanations

    phrases related to optimization and improvement

    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
    eway
    -0.07
    üz
    -0.07
    _consts
    -0.07
    rica
    -0.07
    .times
    -0.06
    à¹Ĩ
    -0.06
     minus
    -0.06
    _fsm
    -0.06
    fet
    -0.06
     Frage
    -0.06
    POSITIVE LOGITS
     existing
    0.07
    umerator
    0.07
     overall
    0.07
    existing
    0.07
    åİŁæľ¬
    0.06
    ạc
    0.06
     otherwise
    0.06
    ya
    0.06
    overall
    0.06
    ีà¸Ńย
    0.06
    Activations Density 0.033%

    No Known Activations