© 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. 25-LLAMASCOPE-RES-32K
    11. 13369
    Prev
    Next
    INDEX
    Explanations

    actions and states related to checking in and assessing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uen
    -0.15
    리ìĸ´
    -0.14
     obr
    -0.14
    840
    -0.14
    imoto
    -0.14
    925
    -0.14
     interrogation
    -0.14
    onga
    -0.14
    378
    -0.13
    InvalidOperationException
    -0.13
    POSITIVE LOGITS
    -in
    0.84
    -IN
    0.63
    -In
    0.61
    -ins
    0.45
     IN
    0.43
    _in
    0.42
    .in
    0.41
    IN
    0.40
    _IN
    0.36
     In
    0.34
    Activations Density 0.311%

    No Known Activations