© 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. 106828
    Prev
    Next
    INDEX
    Explanations

    references to independent and lesser-known music and films

    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
    NavController
    -0.07
    ủy
    -0.07
    iid
    -0.06
    erland
    -0.06
    celik
    -0.06
    dummy
    -0.06
    jure
    -0.06
     âĩ
    -0.06
     athe
    -0.06
    uid
    -0.06
    POSITIVE LOGITS
     obscure
    0.15
     niche
    0.12
     smaller
    0.10
     obs
    0.10
     small
    0.10
    small
    0.09
     lesser
    0.09
     unheard
    0.09
     local
    0.08
     nich
    0.08
    Activations Density 0.052%

    No Known Activations