© 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. 60764
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate complete or total inclusion

    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
    andom
    -0.06
    886
    -0.06
     innoc
    -0.05
     and
    -0.05
    :↵
    -0.05
    era
    -0.05
     :↵
    -0.05
    inke
    -0.05
    [out
    -0.05
     voc
    -0.05
    POSITIVE LOGITS
    cheid
    0.09
    maj
    0.08
    izen
    0.08
    etheless
    0.08
    ìŀĸ
    0.07
    uien
    0.07
    ži
    0.07
    owing
    0.07
    oins
    0.07
    uxtap
    0.07
    Activations Density 0.028%

    No Known Activations