© 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. 29017
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or intentions

    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
    asar
    -0.09
     наÑģÑĤ
    -0.08
    cplusplus
    -0.07
    orna
    -0.07
    .opens
    -0.07
    ond
    -0.07
    itoris
    -0.07
    asca
    -0.07
    rans
    -0.07
    ylan
    -0.07
    POSITIVE LOGITS
     possible
    0.09
     possibile
    0.08
     posible
    0.07
     possÃŃvel
    0.07
    åı¯èĥ½
    0.07
     ever
    0.06
     counterparts
    0.06
     possibly
    0.06
    possible
    0.06
     Possible
    0.06
    Activations Density 0.012%

    No Known Activations