© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 20771
    Prev
    Next
    INDEX
    Explanations

    phrases indicating requests, obligations, and communication regarding processes and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isci
    -0.13
    ãĥ¼ãĥĭ
    -0.13
    ãĥ³ãĥĩãĤ£
    -0.12
     åıĪ
    -0.12
    ÙĤÛĮ
    -0.12
     dopo
    -0.12
    cela
    -0.12
    outers
    -0.12
     ÎĶι
    -0.12
    bakan
    -0.12
    POSITIVE LOGITS
     beforehand
    0.66
     ahead
    0.60
     upfront
    0.53
     Ahead
    0.51
    ahead
    0.50
     advance
    0.49
    Ahead
    0.47
    -ahead
    0.46
     prior
    0.41
    advance
    0.40
    Activations Density 0.571%

    No Known Activations