© 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. 25-LLAMASCOPE-RES-32K
    11. 18418
    Prev
    Next
    INDEX
    Explanations

    technical or specialized vocabulary related to system dynamics and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oz
    -0.16
     sham
    -0.15
    ading
    -0.15
    YP
    -0.14
     double
    -0.14
    obby
    -0.14
    oks
    -0.14
    ling
    -0.14
    omen
    -0.13
    924
    -0.13
    POSITIVE LOGITS
    ÂłkW
    0.17
    acha
    0.16
    صÙĪر
    0.15
    Å¡ka
    0.15
    áo
    0.14
    _MACRO
    0.14
    @register
    0.14
    δÏİ
    0.14
    vé
    0.14
     demek
    0.14
    Activations Density 0.018%

    No Known Activations