Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 57406
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "Mon" or its variations in different 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
    itious
    -0.07
    üst
    -0.07
    raud
    -0.06
    versible
    -0.06
    led
    -0.06
    ytut
    -0.06
    pest
    -0.06
    unker
    -0.06
    MAND
    -0.06
     Mann
    -0.06
    POSITIVE LOGITS
    aghan
    0.08
    ochrome
    0.08
    itored
    0.08
    roe
    0.08
    astery
    0.08
    ITOR
    0.07
    aco
    0.07
    sters
    0.07
    mor
    0.07
     nom
    0.07
    Activations Density 0.009%

    No Known Activations