© 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. 15-LLAMASCOPE-RES-131K
    6. 27172
    Prev
    Next
    INDEX
    Explanations

    references to job positions and governmental appointments

    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
    æŁĦ
    -0.07
    Щ
    -0.07
    sted
    -0.07
    770
    -0.07
    agle
    -0.06
    _INTR
    -0.06
    ลา
    -0.06
    .handleError
    -0.06
    ëĨ
    -0.06
    agu
    -0.06
    POSITIVE LOGITS
    zej
    0.07
     resulting
    0.06
    ispecies
    0.06
    irse
    0.06
    abler
    0.06
     unless
    0.06
    RS
    0.06
     accordingly
    0.06
     via
    0.06
    preneur
    0.06
    Activations Density 0.017%

    No Known Activations