© 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. 17-LLAMASCOPE-RES-131K
    11. 60779
    Prev
    Next
    INDEX
    Explanations

    mentions of steel and related terms

    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
    etic
    -0.09
    es
    -0.08
    eck
    -0.08
    ethe
    -0.07
    done
    -0.07
    esc
    -0.07
    ellen
    -0.06
    eniable
    -0.06
    eldon
    -0.06
    jo
    -0.06
    POSITIVE LOGITS
    workers
    0.10
    inox
    0.08
    zeug
    0.08
    boro
    0.07
    -gray
    0.07
    works
    0.07
    ambre
    0.07
    -grey
    0.07
    neck
    0.07
    sonian
    0.07
    Activations Density 0.009%

    No Known Activations