© 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. 6536
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "disabled" and related context about limitations or lack of functionality

    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
    ursday
    -0.15
    社
    -0.15
    kou
    -0.15
    ünd
    -0.14
    comed
    -0.14
     light
    -0.14
    orgh
    -0.14
    ģ
    -0.14
    204
    -0.14
     Sho
    -0.14
    POSITIVE LOGITS
    etch
    0.17
    ãĥ³ãĥij
    0.17
    ingly
    0.16
    uzu
    0.15
    ãģĴ
    0.15
    chip
    0.14
    ade
    0.14
    ÃŃm
    0.14
    opic
    0.14
    ville
    0.14
    Activations Density 0.000%

    No Known Activations