© 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. 17-LLAMASCOPE-RES-131K
    6. 118904
    Prev
    Next
    INDEX
    Explanations

    attributes and properties related to web resources or metadata

    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
    istrict
    -0.06
     cottage
    -0.06
    ihan
    -0.06
    annot
    -0.06
    nder
    -0.06
    iface
    -0.05
    onia
    -0.05
    etta
    -0.05
     McMaster
    -0.05
    lej
    -0.05
    POSITIVE LOGITS
    ource
    0.08
    tual
    0.07
    ocos
    0.07
    ypad
    0.06
     Petr
    0.06
    lamaz
    0.06
    ignKey
    0.06
     ben
    0.06
    adan
    0.06
     Wand
    0.06
    Activations Density 0.001%

    No Known Activations