Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119357
    Prev
    Next
    INDEX
    Explanations

    expressions of desire, affection, and appreciation

    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
    exter
    -0.07
    ÄĽÅ¾
    -0.07
     etc
    -0.07
    otas
    -0.06
    ιÏĩ
    -0.06
    _SPECIAL
    -0.06
    afi
    -0.06
     much
    -0.06
    adu
    -0.06
    amil
    -0.06
    POSITIVE LOGITS
     Dre
    0.07
    abant
    0.07
     recess
    0.06
    iare
    0.06
    rud
    0.06
     Dere
    0.06
    alink
    0.06
    ysl
    0.06
    uda
    0.06
    assy
    0.05
    Activations Density 0.009%

    No Known Activations