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. 9-LLAMASCOPE-RES-131K
    6. 95920
    Prev
    Next
    INDEX
    Explanations

    references to studies and models in research 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
     sund
    -0.07
    IGN
    -0.06
    nick
    -0.06
    cla
    -0.06
    oine
    -0.06
    nun
    -0.06
    sic
    -0.06
    eniz
    -0.06
    Ã
    -0.06
    unte
    -0.06
    POSITIVE LOGITS
    strup
    0.08
    thon
    0.07
    å¼ķãģį
    0.07
    ãĥĭãĥ¼
    0.07
    issy
    0.07
    omain
    0.06
    akens
    0.06
    翼
    0.06
     Artem
    0.06
    ForObject
    0.06
    Activations Density 0.088%

    No Known Activations