© 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. 125420
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating suggestions or recommendations

    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
     therefore
    -0.08
    raid
    -0.06
     thus
    -0.06
    æĸĻ
    -0.06
     cal
    -0.06
     donc
    -0.05
    ingt
    -0.05
     Berk
    -0.05
     Therefore
    -0.05
     jury
    -0.05
    POSITIVE LOGITS
    acos
    0.08
    urum
    0.08
    Tpl
    0.08
    ready
    0.07
    /GPL
    0.07
    è¼Ŀ
    0.07
    Ready
    0.07
     vur
    0.07
    ileÅŁ
    0.07
     (~(
    0.07
    Activations Density 0.002%

    No Known Activations