Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4929
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be."

    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
    egt
    -0.10
    resse
    -0.09
    gere
    -0.08
    eyer
    -0.07
    ailing
    -0.07
    avig
    -0.07
    /Dk
    -0.07
    irement
    -0.07
    osy
    -0.07
    UIAlert
    -0.07
    POSITIVE LOGITS
    wheel
    0.08
     wheel
    0.08
    -wheel
    0.07
    Wheel
    0.06
    burgh
    0.06
     Wheel
    0.06
     Pend
    0.06
    .respond
    0.06
     Bu
    0.06
    vale
    0.06
    Activations Density 0.002%

    No Known Activations