© 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. 40676
    Prev
    Next
    INDEX
    Explanations

    expressions related to following one's dreams or paths in life

    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
    ninger
    -0.07
    quip
    -0.07
    rag
    -0.07
    egend
    -0.07
    AsyncResult
    -0.06
    rame
    -0.06
    rej
    -0.06
    cycl
    -0.06
    LAG
    -0.06
    achine
    -0.06
    POSITIVE LOGITS
     advice
    0.09
    оÑģÑĮ
    0.08
     instructions
    0.07
     path
    0.07
     directions
    0.07
     followed
    0.07
    ahi
    0.07
     paths
    0.06
     advises
    0.06
     leads
    0.06
    Activations Density 0.016%

    No Known Activations