© 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. 78270
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transition phrases indicating continuity or addition

    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
    lopen
    -0.07
    thy
    -0.07
    üst
    -0.07
    CERT
    -0.06
    anging
    -0.06
    ypad
    -0.06
    менÑĪ
    -0.06
     Exiting
    -0.06
    .SDK
    -0.06
    qui
    -0.06
    POSITIVE LOGITS
     etc
    0.21
    etc
    0.19
     list
    0.13
    çŃī
    0.12
    /etc
    0.12
     ÑĤоÑīо
    0.11
     çŃī
    0.11
     atd
    0.10
     ëĵ±
    0.10
    list
    0.09
    Activations Density 0.148%

    No Known Activations