© 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. 126426
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific brand or product name

    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
     Weiss
    -0.07
    enos
    -0.07
    ooter
    -0.07
    enga
    -0.06
    haps
    -0.06
    anel
    -0.06
    bert
    -0.06
    aded
    -0.06
    emouth
    -0.06
    ANEL
    -0.06
    POSITIVE LOGITS
    ATERIAL
    0.08
    %%%%%%%%
    0.06
    982
    0.06
    fully
    0.06
     chaud
    0.06
    _STATIC
    0.06
    elin
    0.06
    708
    0.06
    indle
    0.06
    bridge
    0.06
    Activations Density 0.002%

    No Known Activations