© 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. 15-LLAMASCOPE-RES-131K
    11. 103954
    Prev
    Next
    INDEX
    Explanations

    concepts related to human existence and individuality

    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
    tran
    -0.08
    atal
    -0.07
    βολ
    -0.07
    abel
    -0.07
    opia
    -0.07
    ritel
    -0.07
    $MESS
    -0.07
     statist
    -0.06
    isper
    -0.06
    itol
    -0.06
    POSITIVE LOGITS
    IPP
    0.07
     individuals
    0.07
    åĩ¡
    0.06
    REST
    0.06
    individual
    0.06
     living
    0.06
    VOID
    0.06
    akte
    0.06
    Formation
    0.06
    UTH
    0.06
    Activations Density 0.040%

    No Known Activations