© 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. 16-LLAMASCOPE-RES-32K
    11. 8097
    Prev
    Next
    INDEX
    Explanations

    numerical references or values 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 @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istrovstvÃŃ
    -0.15
    úsqueda
    -0.15
    _usec
    -0.14
    ERSHEY
    -0.13
    -metadata
    -0.13
    OptionPane
    -0.13
    \Php
    -0.12
    OPTARG
    -0.12
    -caret
    -0.12
    OptionsResolver
    -0.12
    POSITIVE LOGITS
    urum
    0.13
    ãĥ³ãĤ°ãĥ«
    0.13
    iber
    0.12
    iture
    0.12
    ilan
    0.12
    oined
    0.12
    Ìģ
    0.12
    į¼
    0.11
    uder
    0.11
    lx
    0.11
    Activations Density 0.001%

    No Known Activations