© 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. 125452
    Prev
    Next
    INDEX
    Explanations

    instances of transitional phrases that indicate sequence or continuity in the 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
    tons
    -0.07
    rtle
    -0.07
    immer
    -0.06
    å²³
    -0.06
    TON
    -0.06
    usercontent
    -0.06
     susp
    -0.06
    sume
    -0.06
     evac
    -0.06
    point
    -0.06
    POSITIVE LOGITS
    udiant
    0.07
    ault
    0.07
    uters
    0.07
    á»ĭnh
    0.06
    berger
    0.06
    radient
    0.06
     DBG
    0.06
    ecided
    0.06
    asper
    0.06
    oise
    0.06
    Activations Density 0.031%

    No Known Activations