© 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. 87621
    Prev
    Next
    INDEX
    Explanations

    translations of words or phrases

    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
    estr
    -0.07
    istry
    -0.06
    xffff
    -0.06
    istr
    -0.06
    eton
    -0.06
    eki
    -0.06
    rek
    -0.06
    ras
    -0.06
    966
    -0.06
    cid
    -0.06
    POSITIVE LOGITS
    ãĥªãĥ¼ãĤº
    0.07
     into
    0.06
    annot
    0.06
    à¹ģล
    0.06
    ARSE
    0.06
    mps
    0.06
    Äįel
    0.06
    marshaller
    0.06
     differently
    0.06
    .Accessible
    0.06
    Activations Density 0.003%

    No Known Activations