© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 76896
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest careful consideration or caution

    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
    rena
    -0.06
    sip
    -0.06
    amin
    -0.06
    elt
    -0.06
    ORIZ
    -0.06
    edn
    -0.05
    AGO
    -0.05
    ATORY
    -0.05
    ð
    -0.05
     el
    -0.05
    POSITIVE LOGITS
     fact
    0.12
     factor
    0.10
    Factor
    0.09
     dikkate
    0.09
     Factor
    0.09
     Fact
    0.08
    .factor
    0.08
     ÑĥÑĩиÑĤ
    0.08
     consideration
    0.08
    fact
    0.08
    Activations Density 0.023%

    No Known Activations