© 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. 29-LLAMASCOPE-RES-32K
    11. 21074
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an increase or improvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     både
    -0.20
     allerdings
    -0.20
     však
    -0.18
     jedoch
    -0.18
    ocre
    -0.16
    -ÑĤо
    -0.16
     HOWEVER
    -0.15
     nejd
    -0.15
    richt
    -0.15
    ÑģÑĮ
    -0.15
    POSITIVE LOGITS
    /or
    1.11
    /OR
    0.65
    rogen
    0.42
    /of
    0.42
    ä¸Ķ
    0.41
    rog
    0.40
     hence
    0.39
    /o
    0.39
    наÑĩе
    0.39
    rew
    0.38
    Activations Density 1.956%

    No Known Activations