© 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. 83082
    Prev
    Next
    INDEX
    Explanations

    colloquial expressions and personal experiences related to social comparison

    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
    _INCREF
    -0.06
    IODevice
    -0.06
    Compat
    -0.06
    yonel
    -0.06
    adiens
    -0.06
    rama
    -0.06
    ugo
    -0.06
    oki
    -0.06
     Kew
    -0.06
    aper
    -0.06
    POSITIVE LOGITS
    YPES
    0.07
    chner
    0.07
    ãĢħ
    0.07
    λÏİ
    0.07
    riad
    0.07
    ìĤ°
    0.07
    ooth
    0.07
    翼
    0.06
    uros
    0.06
    COLUMN
    0.06
    Activations Density 0.022%

    No Known Activations