© 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. 3810
    Prev
    Next
    INDEX
    Explanations

    references to promotional or advertising content

    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
    asca
    -0.06
     partition
    -0.06
     Sammy
    -0.06
    anki
    -0.06
    bih
    -0.06
    .
    -0.06
     rud
    -0.05
    URRED
    -0.05
    üf
    -0.05
    umann
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĥĸ
    0.09
    ãĥ³ãĥĩ
    0.08
    Å¡ov
    0.07
    .spotify
    0.07
    .geom
    0.07
    HEME
    0.07
    .twitch
    0.07
     ValueEventListener
    0.07
    amil
    0.07
    ế
    0.07
    Activations Density 0.000%

    No Known Activations