© 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. 103738
    Prev
    Next
    INDEX
    Explanations

    verbs related to selection and consumption

    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
    monic
    -0.07
    meni
    -0.07
    ingers
    -0.06
    ãĤ·ãĥ§
    -0.06
    ãĥĥãĤ·ãĥ¥
    -0.06
    веÑī
    -0.06
    erves
    -0.06
     Ting
    -0.06
    els
    -0.06
    asl
    -0.06
    POSITIVE LOGITS
    APT
    0.07
    668
    0.07
    ysz
    0.07
    ttp
    0.07
    زار
    0.07
    595
    0.07
     konkrét
    0.07
    415
    0.06
    YPRE
    0.06
    sar
    0.06
    Activations Density 0.017%

    No Known Activations