© 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. 60615
    Prev
    Next
    INDEX
    Explanations

    numeric values and their characteristics in a statistical context

    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
    ripple
    -0.08
    sky
    -0.07
     kum
    -0.07
    resi
    -0.07
    emark
    -0.06
    ission
    -0.06
    issions
    -0.06
    dub
    -0.06
    ÑĤÑĢа
    -0.06
    intage
    -0.06
    POSITIVE LOGITS
     unto
    0.07
    елик
    0.06
    oods
    0.06
    ibly
    0.06
    `.`
    0.06
    ÙĤب
    0.06
    Messenger
    0.06
    .central
    0.06
     Slo
    0.06
    juan
    0.05
    Activations Density 0.000%

    No Known Activations