© 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. 103782
    Prev
    Next
    INDEX
    Explanations

    terms related to image resolutions and file versions

    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
    иÑĩ
    -0.06
    ildo
    -0.06
    ariant
    -0.06
    urch
    -0.06
    alace
    -0.05
    ibar
    -0.05
    azed
    -0.05
    icensed
    -0.05
    enza
    -0.05
    rib
    -0.05
    POSITIVE LOGITS
    _intent
    0.08
     nao
    0.07
    *>*
    0.07
    Restricted
    0.07
    .xr
    0.07
    uvre
    0.07
     æº
    0.07
    cae
    0.07
    ús
    0.07
    _Property
    0.07
    Activations Density 0.001%

    No Known Activations