© 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. 87619
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific phonetic sequences or patterns in words

    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
    ackbar
    -0.07
    avad
    -0.07
    ALS
    -0.06
     stripslashes
    -0.06
    als
    -0.06
    ÏĦια
    -0.06
    sdale
    -0.06
    _CP
    -0.06
    viso
    -0.06
    AMENT
    -0.06
    POSITIVE LOGITS
    bert
    0.06
    eg
    0.06
     Mein
    0.06
     Damon
    0.06
    stein
    0.06
    rim
    0.06
    kw
    0.06
    stract
    0.06
    obi
    0.06
    amba
    0.06
    Activations Density 0.004%

    No Known Activations