© 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. 55821
    Prev
    Next
    INDEX
    Explanations

    interactions that involve communication and expectations of feedback

    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
    lad
    -0.06
     à¤ļà¤ķ
    -0.06
    isto
    -0.06
    umm
    -0.06
    /assets
    -0.06
    EDIT
    -0.06
    ollah
    -0.06
    lio
    -0.06
    loan
    -0.06
    adel
    -0.06
    POSITIVE LOGITS
    652
    0.07
    ominator
    0.07
     kinds
    0.07
    eya
    0.06
    é³´
    0.06
    annels
    0.06
     Ali
    0.06
    tep
    0.06
    aktu
    0.06
    352
    0.06
    Activations Density 0.004%

    No Known Activations