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

    Neuronpedia

    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. 88113
    Prev
    Next
    INDEX
    Explanations

    references to content that is worth watching or reviewing

    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
    èŃľ
    -0.08
     Vel
    -0.07
    ooter
    -0.06
    izard
    -0.06
    itore
    -0.06
     جÙĦ
    -0.06
    utterstock
    -0.06
    æ£ļ
    -0.06
    è¸ı
    -0.06
     sm
    -0.06
    POSITIVE LOGITS
     Äijá»įc
    0.07
    urat
    0.07
    аниÑĨ
    0.07
    asca
    0.07
    (pdf
    0.07
    çak
    0.07
    _readable
    0.07
    OffsetTable
    0.07
    jav
    0.07
    adius
    0.07
    Activations Density 0.025%

    No Known Activations