© 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. 126317
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events and their impacts

    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
    Ī
    -0.07
    590
    -0.07
    ired
    -0.07
    airs
    -0.06
    theon
    -0.06
    itted
    -0.06
    izo
    -0.06
    zzo
    -0.06
    idla
    -0.06
    nout
    -0.06
    POSITIVE LOGITS
     nackte
    0.09
     Exp
    0.07
     Battle
    0.07
     abort
    0.07
     exp
    0.07
    orman
    0.06
    .TEXTURE
    0.06
    tube
    0.06
    ì§ľ
    0.06
    +:
    0.06
    Activations Density 0.067%

    No Known Activations