© 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. 22-LLAMASCOPE-RES-131K
    11. 4329
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing conditional or hypothetical scenarios

    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
    ading
    -0.07
    artz
    -0.07
     zwar
    -0.06
     contain
    -0.06
    its
    -0.06
    issor
    -0.06
    irs
    -0.06
    oa
    -0.06
    isclosed
    -0.06
    era
    -0.06
    POSITIVE LOGITS
     accompanies
    0.16
     accompany
    0.14
     comes
    0.14
     come
    0.12
    comes
    0.10
     accompanied
    0.10
    Come
    0.10
    come
    0.10
     ens
    0.10
     Comes
    0.10
    Activations Density 0.024%

    No Known Activations