© 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. 118560
    Prev
    Next
    INDEX
    Explanations

    elements related to sensory experiences and food preparation

    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
    alus
    -0.07
    aro
    -0.06
     Tomorrow
    -0.06
     vinden
    -0.06
    _found
    -0.05
    eron
    -0.05
    illez
    -0.05
    avana
    -0.05
    ellas
    -0.05
    zier
    -0.05
    POSITIVE LOGITS
    ãĤ¤ãĤº
    0.08
    inci
    0.08
    resco
    0.08
    Gratis
    0.07
    Uniform
    0.07
    PIP
    0.07
    .gwt
    0.07
    ạm
    0.07
    stamp
    0.07
     Ferm
    0.07
    Activations Density 0.003%

    No Known Activations