© 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. 87096
    Prev
    Next
    INDEX
    Explanations

    specific publication details and references

    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
     cih
    -0.07
    нож
    -0.07
    ÙĨÛĮ
    -0.07
    ablo
    -0.07
    ниÑĤ
    -0.07
    ÑĢовиÑĩ
    -0.07
    jian
    -0.06
    atican
    -0.06
    idata
    -0.06
    doch
    -0.06
    POSITIVE LOGITS
     Vol
    0.07
     volume
    0.07
     vol
    0.07
     Volume
    0.07
    Invariant
    0.07
    volume
    0.06
    icontrol
    0.06
    vol
    0.06
    arton
    0.06
    Vol
    0.06
    Activations Density 0.065%

    No Known Activations