© 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. 84072
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and processes aimed at achieving a goal or outcome

    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
    _published
    -0.07
    ysz
    -0.07
    otal
    -0.06
    oola
    -0.06
    tid
    -0.06
    acht
    -0.06
     çĽ
    -0.06
    زد
    -0.06
    FFFFFFFF
    -0.06
    chwitz
    -0.06
    POSITIVE LOGITS
     successful
    0.10
     successfully
    0.09
     suc
    0.07
     properly
    0.07
     proper
    0.07
     safely
    0.07
     complete
    0.07
     succès
    0.07
    reon
    0.07
     fully
    0.06
    Activations Density 0.034%

    No Known Activations