© 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. 15-LLAMASCOPE-RES-131K
    11. 26819
    Prev
    Next
    INDEX
    Explanations

    references to community engagement and collaboration

    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
    (åľŁ
    -0.08
    riott
    -0.07
    angan
    -0.07
    veau
    -0.07
    achat
    -0.07
    ÑĪка
    -0.07
    akra
    -0.07
    fahren
    -0.07
     Synd
    -0.07
    argin
    -0.07
    POSITIVE LOGITS
     sheet
    0.07
    ditor
    0.06
     Hal
    0.06
     dereg
    0.06
     groups
    0.06
     sing
    0.06
     Merc
    0.06
    HEET
    0.06
     fold
    0.06
     isolated
    0.06
    Activations Density 0.021%

    No Known Activations