© 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. 28875
    Prev
    Next
    INDEX
    Explanations

    actions related to the removal or loss of position and responsibilities

    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
    afs
    -0.08
    sole
    -0.07
     lParam
    -0.07
    ắm
    -0.07
    .twig
    -0.07
    horn
    -0.06
    orama
    -0.06
    quet
    -0.06
    -aged
    -0.06
    ê±°ëŀĺ
    -0.06
    POSITIVE LOGITS
     status
    0.09
     membership
    0.09
     official
    0.07
     privileges
    0.07
    membership
    0.07
     license
    0.07
     Status
    0.07
    status
    0.07
     privilege
    0.07
    åĺ
    0.07
    Activations Density 0.014%

    No Known Activations