© 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. 15-LLAMASCOPE-RES-131K
    11. 61810
    Prev
    Next
    INDEX
    Explanations

    references to business and market dynamics

    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
    IDDEN
    -0.09
    poz
    -0.08
    istrovstvÃŃ
    -0.08
    ãĥ¼ãĥľ
    -0.07
    esModule
    -0.07
    Це
    -0.07
    umbo
    -0.07
    _mE
    -0.07
    IELD
    -0.07
    SetActive
    -0.07
    POSITIVE LOGITS
     products
    0.06
    ack
    0.06
    ortic
    0.06
    ix
    0.05
     mixes
    0.05
     co
    0.05
     Cit
    0.05
    open
    0.05
     повеÑĢÑħ
    0.05
    计
    0.05
    Activations Density 0.004%

    No Known Activations