© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4180
    Prev
    Next
    INDEX
    Explanations

    the prefix "isc" in various contexts

    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
    atten
    -0.06
    weis
    -0.06
    izzato
    -0.06
    leted
    -0.06
    uele
    -0.06
    ktion
    -0.06
    verting
    -0.05
    leting
    -0.05
    kbd
    -0.05
    ainties
    -0.05
    POSITIVE LOGITS
    illa
    0.10
    ILLA
    0.07
    illian
    0.07
    esco
    0.07
    olla
    0.06
     Kara
    0.06
    coli
    0.06
    ario
    0.06
     facult
    0.06
    andra
    0.06
    Activations Density 0.001%

    No Known Activations