© 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. 106480
    Prev
    Next
    INDEX
    Explanations

    phrases focused on collective experiences and shared sentiments

    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
    eyi
    -0.06
    è¾°
    -0.06
    aca
    -0.06
    ngr
    -0.06
    portlet
    -0.06
    .initState
    -0.06
    ades
    -0.06
    άÏĥ
    -0.06
    )const
    -0.06
     Infect
    -0.06
    POSITIVE LOGITS
    atro
    0.07
    abar
    0.06
    igne
    0.06
    riel
    0.06
     overlooked
    0.06
    pent
    0.06
    rne
    0.06
    uela
    0.06
     can
    0.06
    351
    0.06
    Activations Density 0.025%

    No Known Activations