© 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. 60774
    Prev
    Next
    INDEX
    Explanations

    code-related comments or annotations

    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
    stre
    -0.07
    woff
    -0.07
    dez
    -0.07
    .cn
    -0.06
    ses
    -0.06
    sher
    -0.06
     ed
    -0.06
    readcr
    -0.06
    "go
    -0.06
    óng
    -0.06
    POSITIVE LOGITS
    ylon
    0.07
    eki
    0.06
     partner
    0.06
    arton
    0.06
    967
    0.06
    ŀæĢ§
    0.06
    fty
    0.06
    WithDuration
    0.06
    .codes
    0.06
    CLUD
    0.06
    Activations Density 0.000%

    No Known Activations