© 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. 9-LLAMASCOPE-RES-131K
    11. 95558
    Prev
    Next
    INDEX
    Explanations

    concepts related to agricultural extension and training

    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
    mlin
    -0.08
    pmat
    -0.08
    vell
    -0.07
    átek
    -0.07
    razil
    -0.07
    bral
    -0.07
    ouse
    -0.07
    anson
    -0.07
    yat
    -0.07
    abant
    -0.07
    POSITIVE LOGITS
    athers
    0.07
    idente
    0.06
    746
    0.06
    56
    0.06
    \Mapping
    0.06
     Maria
    0.06
    iv
    0.05
    ÑĤÑİ
    0.05
    çĤİ
    0.05
     micron
    0.05
    Activations Density 0.014%

    No Known Activations