© 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. 56331
    Prev
    Next
    INDEX
    Explanations

    references to telecommunications and related technologies

    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
    opoulos
    -0.08
    elight
    -0.07
    izedName
    -0.07
    uli
    -0.07
    är
    -0.07
    icus
    -0.07
    jal
    -0.06
    eel
    -0.06
    hol
    -0.06
     Yug
    -0.06
    POSITIVE LOGITS
     Aviv
    0.10
    éfono
    0.09
     italia
    0.06
    iminal
    0.06
    ented
    0.06
    endir
    0.06
    271
    0.06
    sets
    0.06
    rick
    0.06
    bian
    0.06
    Activations Density 0.011%

    No Known Activations