© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 26853
    Prev
    Next
    INDEX
    Explanations

    strong negative emotions or conditions associated with undesirability

    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
    pras
    -0.09
    ãĥ¼ãĥĩ
    -0.08
    berapa
    -0.08
    yd
    -0.07
    vier
    -0.07
    rych
    -0.07
    atrice
    -0.07
    inem
    -0.07
    hra
    -0.07
    ÑĢеÑģ
    -0.07
    POSITIVE LOGITS
     prov
    0.06
     ve
    0.06
    å¶
    0.06
     “â̦
    0.06
     confront
    0.05
     borders
    0.05
     smb
    0.05
     sediment
    0.05
    gaard
    0.05
    Viewer
    0.05
    Activations Density 0.000%

    No Known Activations