© 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. 5-LLAMASCOPE-RES-131K
    11. 125997
    Prev
    Next
    INDEX
    Explanations

    mentions of interaction

    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
    òa
    -0.07
    aret
    -0.07
    inea
    -0.07
    hana
    -0.06
     rehe
    -0.06
    rana
    -0.06
    еÑĢÑĤа
    -0.06
     ActionTypes
    -0.06
    jours
    -0.06
    owie
    -0.06
    POSITIVE LOGITS
    uality
    0.08
    UAL
    0.08
    ual
    0.07
    swith
    0.07
    uating
    0.07
    uated
    0.07
    905
    0.06
    apes
    0.06
    087
    0.06
     Swarm
    0.06
    Activations Density 0.014%

    No Known Activations