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. 61019
    Prev
    Next
    INDEX
    Explanations

    references to sequences or multiples in various contexts

    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
    elen
    -0.06
    bang
    -0.06
    quares
    -0.06
     respectively
    -0.06
    amba
    -0.06
    ady
    -0.05
    kola
    -0.05
    Äįel
    -0.05
    åIJ¹
    -0.05
     all
    -0.05
    POSITIVE LOGITS
    ochond
    0.07
     sixth
    0.07
    /add
    0.07
    ancellationToken
    0.07
     fifth
    0.07
     layer
    0.07
     seventh
    0.07
    aryawan
    0.07
    CAC
    0.06
    PCS
    0.06
    Activations Density 0.027%

    No Known Activations