Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 21-LLAMASCOPE-RES-32K
    6. 17558
    Prev
    Next
    INDEX
    Explanations

    instructions related to measuring and constructing physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Filtering
    -0.17
    CHA
    -0.17
     filtering
    -0.16
     bomb
    -0.15
    unan
    -0.15
    Cha
    -0.14
     γεÏģ
    -0.14
     mushroom
    -0.14
    -medium
    -0.14
     compact
    -0.14
    POSITIVE LOGITS
     measurement
    0.31
     measuring
    0.31
     measurements
    0.31
     Measurements
    0.28
     Measurement
    0.28
    measurement
    0.27
    measure
    0.27
    .measure
    0.27
    Measure
    0.26
    Measurement
    0.26
    Activations Density 0.118%

    No Known Activations