© 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. 87181
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements related to instructions or guidelines

    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
    ello
    -0.07
    noinspection
    -0.07
    zin
    -0.07
    cas
    -0.06
    ायत
    -0.06
    itchen
    -0.06
    با
    -0.06
    utherland
    -0.06
    agan
    -0.06
    æıIJ
    -0.06
    POSITIVE LOGITS
    licken
    0.07
     distinct
    0.06
    eldorf
    0.06
    ureau
    0.06
     distinctive
    0.06
     pathMatch
    0.06
    etheless
    0.06
    StackSize
    0.06
    emailer
    0.06
    abei
    0.06
    Activations Density 0.084%

    No Known Activations