© 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. 106126
    Prev
    Next
    INDEX
    Explanations

    references to cooking methods or techniques

    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
    ะ
    -0.08
    ROME
    -0.07
    oit
    -0.07
    pest
    -0.07
    ispecies
    -0.06
    ileo
    -0.06
    idan
    -0.06
    porto
    -0.06
    ignum
    -0.06
    ultipart
    -0.06
    POSITIVE LOGITS
    er
    0.10
    nda
    0.09
    ingly
    0.09
    ers
    0.08
    igg
    0.07
    ee
    0.07
    outs
    0.07
    çīĩ
    0.07
    ings
    0.07
    out
    0.07
    Activations Density 0.006%

    No Known Activations