© 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. 29477
    Prev
    Next
    INDEX
    Explanations

    instances of technical specifications and documentation references

    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
    .scalablytyped
    -0.07
     기
    -0.06
    jax
    -0.06
    akis
    -0.06
    ery
    -0.06
    akin
    -0.06
    acas
    -0.06
     appropriations
    -0.06
    514
    -0.06
     Tradable
    -0.06
    POSITIVE LOGITS
    edith
    0.07
     Mog
    0.07
    venta
    0.07
     Blow
    0.06
    gency
    0.06
    hints
    0.06
    SEMB
    0.06
    GENCY
    0.06
    ÏĢα
    0.06
    μιÏĥ
    0.06
    Activations Density 0.000%

    No Known Activations