© 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. 40600
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to successful outcomes or achievements

    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
     latest
    -0.07
    latest
    -0.06
    iminal
    -0.06
    ICE
    -0.06
     knocks
    -0.06
     knocking
    -0.06
     Latest
    -0.06
    aub
    -0.06
    zug
    -0.06
    anch
    -0.06
    POSITIVE LOGITS
    igon
    0.08
    igua
    0.07
    igo
    0.07
    ika
    0.07
     similarly
    0.07
     vé
    0.07
    ig
    0.06
    ampa
    0.06
    decorators
    0.06
    olik
    0.06
    Activations Density 0.009%

    No Known Activations