© 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 EvalsExportsinterp-engineNEWAPI 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. 94768
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and the activities associated with them

    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
    FLOAT
    -0.07
    ëŀ
    -0.07
    arten
    -0.07
    .Magenta
    -0.07
    @student
    -0.07
    ILE
    -0.07
    ä½Ļ
    -0.07
    uç
    -0.07
    ť
    -0.07
    ween
    -0.07
    POSITIVE LOGITS
     finally
    0.18
    finally
    0.15
     Finally
    0.13
    Finally
    0.12
     poprvé
    0.12
     again
    0.12
     unprecedented
    0.12
     now
    0.12
    ç»Īäºİ
    0.11
     instead
    0.11
    Activations Density 0.051%

    No Known Activations