Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5403
    Prev
    Next
    INDEX
    Explanations

    phrases indicating current or immediate actions

    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
    chia
    -0.07
     Esk
    -0.07
    ickle
    -0.07
    chal
    -0.07
    ÅĻez
    -0.07
    .Operator
    -0.07
    lag
    -0.06
     NOTES
    -0.06
    èm
    -0.06
    YST
    -0.06
    POSITIVE LOGITS
     reun
    0.06
     Tal
    0.06
     Dick
    0.06
    EMU
    0.05
    ohan
    0.05
     net
    0.05
    orf
    0.05
     reap
    0.05
    LOPT
    0.05
     Kra
    0.05
    Activations Density 0.000%

    No Known Activations