© 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. 95576
    Prev
    Next
    INDEX
    Explanations

    mentions of office locations and organizational structure

    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
    unning
    -0.06
     reigning
    -0.06
    ual
    -0.06
    inct
    -0.06
     category
    -0.05
    ping
    -0.05
    isci
    -0.05
    -major
    -0.05
    å¯Ħ
    -0.05
     furnishings
    -0.05
    POSITIVE LOGITS
     embr
    0.08
    ----</
    0.07
     Ni
    0.07
    NEY
    0.07
    elden
    0.07
    iminal
    0.07
    ---</
    0.07
    ableView
    0.07
    dge
    0.07
    uv
    0.07
    Activations Density 0.010%

    No Known Activations