© 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. 23-LLAMASCOPE-RES-32K
    11. 21360
    Prev
    Next
    INDEX
    Explanations

    ranks and titles within military and authoritative contexts

    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
     Officer
    -0.14
    ersh
    -0.14
    -away
    -0.14
    uce
    -0.14
    /reset
    -0.14
     thá»ķ
    -0.14
    Mr
    -0.14
     Pastor
    -0.14
    modifiable
    -0.14
    clipse
    -0.14
    POSITIVE LOGITS
    amba
    0.15
     запаÑģ
    0.15
    owie
    0.15
    zion
    0.14
     retir
    0.14
    ojis
    0.14
    лей
    0.14
    oyer
    0.14
    lech
    0.13
    864
    0.13
    Activations Density 0.054%

    No Known Activations