© 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. 119568
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and conjunctions linking sections of text

    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
     rev
    -0.07
    istencia
    -0.06
    ait
    -0.06
    åŁ
    -0.06
    ongyang
    -0.06
     fin
    -0.06
    hardt
    -0.06
    ollen
    -0.06
     entry
    -0.06
     routes
    -0.06
    POSITIVE LOGITS
    iq
    0.07
    TTY
    0.06
    ilog
    0.06
    dehy
    0.06
    vsp
    0.06
    elog
    0.06
    oment
    0.06
    /GPL
    0.06
     Broad
    0.06
    FFFFFFFF
    0.06
    Activations Density 0.002%

    No Known Activations