© 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. 17-LLAMASCOPE-RES-131K
    6. 76911
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "was" and instances of events being held

    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
     Applies
    -0.06
    ansa
    -0.06
    efined
    -0.06
    елÑĸ
    -0.06
    oose
    -0.06
    arehouse
    -0.05
     compensated
    -0.05
     capit
    -0.05
    Inv
    -0.05
    oot
    -0.05
    POSITIVE LOGITS
     attended
    0.07
    AAD
    0.07
    .tencent
    0.06
    YD
    0.06
    .Interop
    0.06
     thú
    0.06
    irectional
    0.06
     split
    0.06
     dir
    0.06
    tim
    0.06
    Activations Density 0.018%

    No Known Activations