© 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. 20-LLAMASCOPE-RES-32K
    11. 21640
    Prev
    Next
    INDEX
    Explanations

    keywords related to social dynamics and inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ẽ
    -0.15
    rani
    -0.15
    assing
    -0.14
    ego
    -0.14
    ose
    -0.14
    forcing
    -0.14
    riot
    -0.14
    uze
    -0.14
    Ïģα
    -0.14
    gett
    -0.14
    POSITIVE LOGITS
    imo
    0.15
    erken
    0.15
    ÙħاÙĨ
    0.14
     tab
    0.13
     parch
    0.13
    797
    0.13
    æĺĵ
    0.13
    ãģ«ãģªãĤĬ
    0.13
    623
    0.12
    _FRAME
    0.12
    Activations Density 0.007%

    No Known Activations