© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 12796
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical and cognitive difficulties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Corner
    -0.14
    ród
    -0.14
    ÑĥÑī
    -0.14
    ktop
    -0.14
    izar
    -0.14
    tail
    -0.13
     consts
    -0.13
    -lg
    -0.13
    zl
    -0.13
     exhaust
    -0.13
    POSITIVE LOGITS
     walk
    0.29
     walking
    0.28
    walk
    0.26
     speak
    0.25
     walks
    0.25
     speech
    0.25
     speaking
    0.23
     walker
    0.23
     walked
    0.23
     Walk
    0.22
    Activations Density 0.161%

    No Known Activations