© 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. 84001
    Prev
    Next
    INDEX
    Explanations

    references to single-use or individual items 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
    soever
    -0.07
    grund
    -0.06
    bose
    -0.06
    nas
    -0.06
    abb
    -0.06
    cken
    -0.06
    iform
    -0.06
    agos
    -0.06
    %%%%%%%%
    -0.06
    sj
    -0.06
    POSITIVE LOGITS
    /single
    0.14
    tons
    0.12
    (single
    0.11
    -single
    0.11
     single
    0.10
     SINGLE
    0.09
     Single
    0.09
     solitary
    0.08
     giản
    0.08
    Single
    0.08
    Activations Density 0.022%

    No Known Activations