© 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. 15-LLAMASCOPE-RES-131K
    11. 103741
    Prev
    Next
    INDEX
    Explanations

    descriptors related to physical characteristics and suitability of materials

    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
    urre
    -0.07
    URRE
    -0.07
     pseud
    -0.06
     fellow
    -0.06
     relatively
    -0.06
     Till
    -0.06
    u
    -0.06
    íıIJ
    -0.06
     publicly
    -0.06
    MAND
    -0.06
    POSITIVE LOGITS
    áv
    0.08
    ạn
    0.07
    год
    0.07
    ebek
    0.07
    iyon
    0.07
    lus
    0.07
    .strict
    0.07
    rieb
    0.07
    ftype
    0.07
    аÑħ
    0.07
    Activations Density 0.003%

    No Known Activations