© 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. 71128
    Prev
    Next
    INDEX
    Explanations

    mentions of ghosts and paranormal activities

    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
     huy
    -0.07
    ÑĢÑĮ
    -0.07
    digit
    -0.07
    loub
    -0.07
    ãĥ³ãĤ¯
    -0.07
    çĴĥ
    -0.07
    amerate
    -0.06
    arrings
    -0.06
    ificent
    -0.06
    á»ģ
    -0.06
    POSITIVE LOGITS
     phantom
    0.08
     ghost
    0.07
     Myst
    0.06
     Phantom
    0.06
    Ghost
    0.06
     inexp
    0.06
     visitors
    0.06
    è¬
    0.06
     ----------------------------------------------------------------------------↵
    0.06
     partition
    0.06
    Activations Density 0.007%

    No Known Activations