© 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. 126972
    Prev
    Next
    INDEX
    Explanations

    mentions of "New" followed by various geographical terms or locations

    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
    rlen
    -0.09
    ADDE
    -0.09
    qli
    -0.09
    alars
    -0.09
    curacy
    -0.09
    ufs
    -0.09
    loi
    -0.08
    pline
    -0.08
    nts
    -0.08
    lero
    -0.08
    POSITIVE LOGITS
    -
    0.06
    -origin
    0.06
    ,
    0.06
     origin
    0.06
    e
    0.06
     ÂŃ
    0.05
     latter
    0.05
    /New
    0.05
    ish
    0.05
     firm
    0.05
    Activations Density 0.021%

    No Known Activations