© 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. 78776
    Prev
    Next
    INDEX
    Explanations

    instructions related to graphic placement and application

    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
     Hunger
    -0.07
     rods
    -0.07
    arde
    -0.07
    ories
    -0.06
    -many
    -0.06
    acks
    -0.06
    gr
    -0.06
    orth
    -0.06
    bara
    -0.06
     poles
    -0.06
    POSITIVE LOGITS
    ende
    0.07
    elyn
    0.07
    uyết
    0.07
    ramework
    0.06
     Peyton
    0.06
    quina
    0.06
    ENDOR
    0.06
    jez
    0.06
    emens
    0.06
    Cos
    0.06
    Activations Density 0.004%

    No Known Activations