© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 23-LLAMASCOPE-RES-32K
    6. 29641
    Prev
    Next
    INDEX
    Explanations

    instances of numerical data and statistics related to specific topics

    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
     previews
    -0.15
     Tester
    -0.14
    unnable
    -0.14
    é¢Ħè§Ī
    -0.13
    OLE
    -0.13
    ÎŁÎļ
    -0.13
    vod
    -0.13
     infr
    -0.12
     preview
    -0.12
    {{{
    -0.12
    POSITIVE LOGITS
     recording
    0.56
     record
    0.55
    record
    0.49
     records
    0.48
    è®°å½ķ
    0.47
     Recording
    0.46
    Recording
    0.45
     Record
    0.44
    -record
    0.44
     RECORD
    0.44
    Activations Density 0.380%

    No Known Activations