© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 30409
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and connections

    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
    Enlarge
    -0.07
    anders
    -0.07
    amedi
    -0.07
    ÙĪÙĦÙĬÙĪ
    -0.07
    менÑĪ
    -0.07
    etter
    -0.07
    egree
    -0.07
    rego
    -0.07
    ika
    -0.06
    anke
    -0.06
    POSITIVE LOGITS
     Surv
    0.10
     survive
    0.10
     survivors
    0.10
     surviv
    0.10
     survived
    0.10
    Surv
    0.10
     survives
    0.09
     preceded
    0.09
     surviving
    0.08
     survival
    0.08
    Activations Density 0.075%

    No Known Activations