© 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. 77497
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sign" and its variations, indicating emphasis on notifications or indicators

    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
    utsch
    -0.07
    kses
    -0.07
    mdb
    -0.07
    gradient
    -0.07
    endir
    -0.06
    ject
    -0.06
    iggins
    -0.06
     é¦Ļ
    -0.06
     grad
    -0.06
    ixel
    -0.06
    POSITIVE LOGITS
    ificantly
    0.10
    /sign
    0.10
     sign
    0.09
    ificance
    0.09
    atures
    0.09
    ificant
    0.09
    -sign
    0.09
    .SIG
    0.08
    post
    0.08
    (sign
    0.08
    Activations Density 0.009%

    No Known Activations