© 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. 71537
    Prev
    Next
    INDEX
    Explanations

    references to professional development and career progression

    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
    arna
    -0.08
    elu
    -0.06
    zes
    -0.06
    lear
    -0.06
    chin
    -0.06
    enos
    -0.06
    ersen
    -0.06
    --------------------------------
    -0.06
    isson
    -0.06
    oste
    -0.06
    POSITIVE LOGITS
    -long
    0.08
    istically
    0.08
    -ending
    0.07
    -threatening
    0.07
    istic
    0.07
    IDGET
    0.07
     boyunca
    0.07
    ëª
    0.07
    .Cryptography
    0.07
    ümÃ¼ÅŁ
    0.06
    Activations Density 0.017%

    No Known Activations