© 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. 29598
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and numerical values

    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
    deposit
    -0.07
     nuru
    -0.07
    .Formatter
    -0.07
    versible
    -0.07
    469
    -0.07
    edback
    -0.07
    ÅĽnie
    -0.07
    .Automation
    -0.07
    processable
    -0.07
    pls
    -0.07
    POSITIVE LOGITS
    emet
    0.06
    ahlen
    0.06
     tun
    0.06
    CCA
    0.06
    ureau
    0.06
    adden
    0.06
    inge
    0.06
     lookout
    0.06
    innen
    0.05
    orget
    0.05
    Activations Density 0.001%

    No Known Activations