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. 126595
    Prev
    Next
    INDEX
    Explanations

    key thematic or functional elements relating to leadership and operational strategy

    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
    俺
    -0.09
    -ln
    -0.07
    arf
    -0.07
    AffineTransform
    -0.07
    å»
    -0.07
    ReadStream
    -0.07
    İ
    -0.07
    одав
    -0.07
    Modifier
    -0.07
    ovie
    -0.07
    POSITIVE LOGITS
     herself
    0.07
    https
    0.07
    etler
    0.06
    ison
    0.06
     PMID
    0.06
    ัà¸Ļà¸Ķ
    0.06
     Valor
    0.06
    ylko
    0.06
    meyi
    0.06
     women
    0.06
    Activations Density 0.001%

    No Known Activations