© 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. 15-LLAMASCOPE-RES-131K
    11. 103574
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements in 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
    ibble
    -0.08
    geois
    -0.07
    istringstream
    -0.07
    hausen
    -0.07
    ancellable
    -0.07
    rière
    -0.07
    angkan
    -0.07
    buquerque
    -0.06
    ITHUB
    -0.06
    esco
    -0.06
    POSITIVE LOGITS
    egr
    0.06
    пов
    0.06
     Ger
    0.06
    ủ
    0.06
    mans
    0.05
    eeper
    0.05
     Bild
    0.05
     Russ
    0.05
     Fe
    0.05
    elt
    0.05
    Activations Density 0.031%

    No Known Activations