© 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. 5-LLAMASCOPE-RES-131K
    11. 126049
    Prev
    Next
    INDEX
    Explanations

    phrases indicating affiliation or association

    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
    ilde
    -0.08
    AXB
    -0.08
    fern
    -0.08
    ола
    -0.08
    atorium
    -0.07
    oltip
    -0.07
    AREST
    -0.07
    ilded
    -0.07
    FindObject
    -0.07
    pane
    -0.07
    POSITIVE LOGITS
    inae
    0.07
    Äı
    0.07
     ger
    0.06
     Horizon
    0.06
    asm
    0.06
     nhau
    0.06
     Urs
    0.06
     Uph
    0.06
     [
    0.06
     foreign
    0.05
    Activations Density 0.004%

    No Known Activations