© 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. 9-LLAMASCOPE-RES-131K
    11. 95518
    Prev
    Next
    INDEX
    Explanations

    citations and references in academic writing

    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
    idar
    -0.08
    _Tis
    -0.08
    adia
    -0.08
    AREST
    -0.07
    ekk
    -0.07
    PEnd
    -0.07
     odense
    -0.07
    ToPoint
    -0.07
    InitStruct
    -0.07
    ç¿Ķ
    -0.07
    POSITIVE LOGITS
    emic
    0.06
    verse
    0.06
     [
    0.06
     Pil
    0.06
    s
    0.06
     Blasio
    0.05
    i
    0.05
     pil
    0.05
    get
    0.05
     vers
    0.05
    Activations Density 0.007%

    No Known Activations