© 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. 82706
    Prev
    Next
    INDEX
    Explanations

    details about the health benefits and properties of herbal extracts

    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
    ropol
    -0.09
    ripple
    -0.08
    nict
    -0.08
    spm
    -0.07
    祥
    -0.07
    ondon
    -0.07
    å³
    -0.07
    _TAC
    -0.07
    onth
    -0.07
    ÑĢаÑħов
    -0.07
    POSITIVE LOGITS
     flat
    0.06
    -flat
    0.06
     Brad
    0.06
    ottes
    0.06
    flat
    0.06
    .Flat
    0.06
    hist
    0.05
     Flat
    0.05
     Kid
    0.05
    che
    0.05
    Activations Density 0.010%

    No Known Activations