© 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. 83036
    Prev
    Next
    INDEX
    Explanations

    phrases indicating upcoming information or details

    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
    orney
    -0.07
    uraa
    -0.07
    é§
    -0.07
    OLS
    -0.06
    andalone
    -0.06
    OLON
    -0.06
    rlen
    -0.06
    adal
    -0.06
    isu
    -0.06
    usterity
    -0.06
    POSITIVE LOGITS
     details
    0.10
    /details
    0.09
     Details
    0.08
     DETAILS
    0.08
    -details
    0.07
    details
    0.07
    (details
    0.07
    Details
    0.07
    .Detail
    0.07
     Fir
    0.06
    Activations Density 0.014%

    No Known Activations