© 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. 12-LLAMASCOPE-RES-32K
    11. 13851
    Prev
    Next
    INDEX
    Explanations

    dates associated with historical events or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adol
    -0.17
    hlen
    -0.14
    ADVERTISEMENT
    -0.14
    ATE
    -0.13
    azu
    -0.13
    ;base
    -0.13
    inski
    -0.13
    ogr
    -0.13
    ailer
    -0.13
     Howard
    -0.13
    POSITIVE LOGITS
    roj
    0.15
     ÙħÛĮÙĦادÛĮ
    0.15
    δÏħ
    0.14
    arResult
    0.14
    intree
    0.14
    hole
    0.13
    veau
    0.13
    embr
    0.13
    _INCLUDED
    0.13
    robe
    0.13
    Activations Density 0.032%

    No Known Activations