© 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. 61815
    Prev
    Next
    INDEX
    Explanations

    elements related to physicality and tangible objects

    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
    .initState
    -0.09
    _mapper
    -0.08
    央
    -0.07
    BILL
    -0.07
    icher
    -0.07
    šel
    -0.07
     onCancelled
    -0.07
    ÐķС
    -0.07
     cáºŃp
    -0.07
    ải
    -0.07
    POSITIVE LOGITS
    aggable
    0.07
     Ch
    0.06
    ecut
    0.06
     http
    0.06
     economies
    0.06
    agus
    0.06
     my
    0.06
    ↵
    0.05
    orte
    0.05
     living
    0.05
    Activations Density 0.058%

    No Known Activations