© 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. 683
    Prev
    Next
    INDEX
    Explanations

    monetary amounts or pricing information

    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
    ạm
    -0.07
    ATAL
    -0.07
    iko
    -0.07
    kening
    -0.07
    sea
    -0.06
    kre
    -0.06
     Dra
    -0.06
    grad
    -0.06
     Cust
    -0.06
     Carb
    -0.06
    POSITIVE LOGITS
     per
    0.09
    issen
    0.08
     dinh
    0.08
    å·¦åı³
    0.06
    ancellable
    0.06
    atts
    0.06
    cstdlib
    0.06
    lobals
    0.06
    orsk
    0.06
     perl
    0.06
    Activations Density 0.022%

    No Known Activations