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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 957
    Prev
    Next
    INDEX
    Explanations

    terms related to education and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶Į
    -0.16
    hti
    -0.15
     Äijá»į
    -0.14
    ouri
    -0.14
    pherical
    -0.13
    ¶ģ
    -0.13
     ngữ
    -0.13
    arhus
    -0.13
    swire
    -0.13
    ipherals
    -0.13
    POSITIVE LOGITS
    &quot
    0.24
    &gt
    0.22
    &lt
    0.21
    &eacute
    0.20
    &amp
    0.17
     ':
    0.17
    &oacute
    0.16
    &a
    0.16
    &uuml
    0.15
     cookies
    0.14
    Activations Density 0.011%

    No Known Activations