© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75314
    Prev
    Next
    INDEX
    Explanations

    terms related to teleportation mechanics in a gaming 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
    tura
    -0.07
     stereotypes
    -0.06
    åĽ´
    -0.06
     Kaw
    -0.06
     stereotype
    -0.06
    icias
    -0.06
    _PARAMETER
    -0.06
    okes
    -0.06
     Bundy
    -0.06
    iesel
    -0.06
    POSITIVE LOGITS
     teleport
    0.09
     transportation
    0.08
     travel
    0.08
     transport
    0.07
    ãĥĨãĥ«
    0.07
    .instant
    0.07
    Liver
    0.07
    ÏĢο
    0.07
    _travel
    0.07
    QualifiedName
    0.07
    Activations Density 0.017%

    No Known Activations