© 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. 84068
    Prev
    Next
    INDEX
    Explanations

    instances of the word "next" in various contexts

    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
     nouve
    -0.07
    ampler
    -0.07
    donnees
    -0.07
     Cree
    -0.07
    esModule
    -0.07
     нак
    -0.07
    ãİ
    -0.07
     вв
    -0.07
    ncy
    -0.07
    obra
    -0.07
    POSITIVE LOGITS
     Next
    0.08
     next
    0.08
    Next
    0.07
    Unnamed
    0.06
    RIX
    0.06
    NEXT
    0.06
    next
    0.06
    atically
    0.06
    icus
    0.06
    ls
    0.05
    Activations Density 0.006%

    No Known Activations