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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 30929
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the concept of absorption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifik
    -0.19
    stell
    -0.18
    biz
    -0.17
    ches
    -0.16
    el
    -0.16
    upon
    -0.15
    chant
    -0.15
    ament
    -0.15
    odes
    -0.14
     Powder
    -0.14
    POSITIVE LOGITS
    ption
    0.28
    ptions
    0.19
    ible
    0.18
    edImage
    0.18
    ptive
    0.17
    PTION
    0.16
    è¦
    0.16
    iland
    0.16
    ibly
    0.15
    umpt
    0.15
    Activations Density 0.048%

    No Known Activations