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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4548
    Prev
    Next
    INDEX
    Explanations

    references to CDs and compact discs

    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
    y
    -0.07
    hin
    -0.07
    eer
    -0.06
    ç¹Ķ
    -0.06
    894
    -0.06
     Canter
    -0.06
    inc
    -0.06
    e
    -0.06
    lund
    -0.06
    /sources
    -0.06
    POSITIVE LOGITS
    -ROM
    0.11
    /mp
    0.10
    /D
    0.08
    roulette
    0.07
    ioxide
    0.07
    ê½
    0.07
    аÑĢаÑĤ
    0.07
    -INF
    0.07
    /DD
    0.07
    /video
    0.07
    Activations Density 0.010%

    No Known Activations