© 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. 118964
    Prev
    Next
    INDEX
    Explanations

    connections and relationships expressed through the conjunctions "and" and "or."

    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
     kinds
    -0.07
    oulos
    -0.07
    ignum
    -0.06
    ish
    -0.06
    698
    -0.06
    asma
    -0.06
     Preston
    -0.06
    ee
    -0.05
     sorts
    -0.05
    ipe
    -0.05
    POSITIVE LOGITS
     own
    0.08
     approach
    0.08
     ability
    0.08
     arsenal
    0.07
     theirs
    0.07
     abilities
    0.07
     selves
    0.07
     Ùħتر
    0.07
    Ton
    0.07
    panion
    0.07
    Activations Density 0.163%

    No Known Activations