© 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. 76952
    Prev
    Next
    INDEX
    Explanations

    specific topics related to health, agriculture, and research associated with animals and genetics

    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
    riors
    -0.08
    iser
    -0.07
     certs
    -0.06
    Qed
    -0.06
    otech
    -0.06
    ÑijÑĢ
    -0.06
    ableView
    -0.06
    emez
    -0.06
    isers
    -0.06
    alloc
    -0.06
    POSITIVE LOGITS
    -specific
    0.10
    pecific
    0.08
    -wide
    0.08
    DITION
    0.08
    /Table
    0.07
     specific
    0.07
    -focused
    0.07
    _specific
    0.07
    specific
    0.07
    ernal
    0.07
    Activations Density 0.092%

    No Known Activations