© 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. 31-LLAMASCOPE-RES-32K
    11. 3731
    Prev
    Next
    INDEX
    Explanations

    terms related to ocular and visual perception phenomena

    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
    uary
    -0.18
     Consumption
    -0.15
    ãģ¡ãĤĩ
    -0.15
    ÅĻel
    -0.14
    Multiplicity
    -0.14
    ohana
    -0.14
    è®
    -0.13
    sand
    -0.13
    ÙĩÙĨ
    -0.13
    ÅĻes
    -0.13
    POSITIVE LOGITS
     fund
    0.35
     pup
    0.32
     pupil
    0.30
     Fund
    0.27
     Humph
    0.26
     pupils
    0.25
     slit
    0.24
     ton
    0.23
     aber
    0.23
     OCT
    0.23
    Activations Density 0.012%

    No Known Activations