© 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. 106979
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preference or resemblance

    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
    aram
    -0.07
    ystack
    -0.06
    laus
    -0.06
    æ¶
    -0.06
     Evel
    -0.06
     recurs
    -0.06
     sebuah
    -0.06
    jist
    -0.06
    ż
    -0.06
    eyen
    -0.06
    POSITIVE LOGITS
     myself
    0.10
     us
    0.08
     me
    0.07
     him
    0.07
     who
    0.07
     ourselves
    0.07
     McB
    0.07
     ours
    0.07
    ours
    0.06
     thems
    0.06
    Activations Density 0.019%

    No Known Activations