Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106716
    Prev
    Next
    INDEX
    Explanations

    references to adoption and related bureaucratic processes

    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
    onia
    -0.08
    esk
    -0.07
    imator
    -0.07
     оÑĤв
    -0.07
    .AddParameter
    -0.07
    hab
    -0.07
    ullets
    -0.06
    asa
    -0.06
    oltip
    -0.06
    ichen
    -0.06
    POSITIVE LOGITS
     DNA
    0.10
     reunion
    0.09
     biological
    0.08
    DNA
    0.08
    dna
    0.07
     dna
    0.07
     identity
    0.07
     searcher
    0.07
     genetic
    0.07
     Hague
    0.07
    Activations Density 0.026%

    No Known Activations