© 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. 62087
    Prev
    Next
    INDEX
    Explanations

    elements related to functionality and structure

    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
    SError
    -0.08
    ãĥĬãĥ¼
    -0.07
    еÑģа
    -0.07
    agnost
    -0.07
     ÑĦÑĥнда
    -0.07
    oya
    -0.07
    hai
    -0.07
    .rawValue
    -0.07
     AndAlso
    -0.07
    artin
    -0.07
    POSITIVE LOGITS
     otherwise
    0.08
     or
    0.06
     reputation
    0.06
     wid
    0.06
     such
    0.06
    gii
    0.06
     benefit
    0.06
     pod
    0.06
     mind
    0.05
     Pod
    0.05
    Activations Density 0.005%

    No Known Activations