© 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. 28757
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the importance of particular elements in a context, particularly in artistic or design descriptions

    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
    ục
    -0.06
    .gov
    -0.06
    äºĨ解
    -0.06
     mist
    -0.06
    κι
    -0.06
     Conditions
    -0.06
    ipa
    -0.05
    ãģ§ãģĹãĤĩãģĨ
    -0.05
     implications
    -0.05
    _CRE
    -0.05
    POSITIVE LOGITS
    ãĥ¼ãĥį
    0.07
    ODO
    0.07
     hale
    0.07
    aub
    0.06
    afen
    0.06
    egen
    0.06
     Doch
    0.06
    Jackson
    0.06
    AGER
    0.06
    -ui
    0.06
    Activations Density 0.021%

    No Known Activations