© 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. 3234
    Prev
    Next
    INDEX
    Explanations

    references to network characteristics and behaviors in relation to theoretical models and simulations

    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
     hell
    -0.06
    perator
    -0.06
    plat
    -0.06
    má
    -0.06
    emin
    -0.06
    omu
    -0.06
    oran
    -0.06
     Ents
    -0.06
    lops
    -0.06
    pane
    -0.06
    POSITIVE LOGITS
     GIVEN
    0.09
     given
    0.09
    given
    0.07
    ien
    0.07
    esta
    0.07
     Given
    0.07
    ours
    0.07
    ourn
    0.07
    rtl
    0.06
     cases
    0.06
    Activations Density 0.123%

    No Known Activations