© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 5421
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "democracy" and its associated themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ious
    -0.17
    amer
    -0.17
    iously
    -0.15
    jab
    -0.15
    o
    -0.15
    度
    -0.15
    chnitt
    -0.15
    oje
    -0.14
    ÑĢоÑģ
    -0.14
    heard
    -0.14
    POSITIVE LOGITS
    anded
    0.25
     dem
    0.22
     Dem
    0.21
    oral
    0.20
    oted
    0.20
    ilit
    0.20
    uestra
    0.19
    urr
    0.19
    ographics
    0.19
    anding
    0.19
    Activations Density 0.009%

    No Known Activations