© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70939
    Prev
    Next
    INDEX
    Explanations

    tags related to categorizing content

    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
    etheless
    -0.08
    ion
    -0.07
    elon
    -0.06
    APPING
    -0.06
    /boot
    -0.06
    appers
    -0.06
    aat
    -0.06
    VERRIDE
    -0.06
    anse
    -0.06
    omencl
    -0.06
    POSITIVE LOGITS
    cak
    0.07
    fos
    0.07
    heim
    0.07
    #
    0.06
    ringe
    0.06
    ensitive
    0.06
    indh
    0.06
    acas
    0.06
    itzer
    0.06
     Cascade
    0.06
    Activations Density 0.003%

    No Known Activations