© 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. 104040
    Prev
    Next
    INDEX
    Explanations

    information related to financial assistance and debt management

    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
    aho
    -0.08
    ãĤĨ
    -0.06
     reserve
    -0.06
    .Rows
    -0.06
    clamation
    -0.06
    achi
    -0.06
    ssf
    -0.06
    ondon
    -0.06
    icket
    -0.06
    uur
    -0.06
    POSITIVE LOGITS
     Consolid
    0.08
     consolid
    0.08
     consolidation
    0.07
    ogn
    0.07
     erv
    0.07
    澤
    0.07
     consolidated
    0.07
    voices
    0.07
    imetype
    0.07
    agini
    0.06
    Activations Density 0.001%

    No Known Activations