Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 21-LLAMASCOPE-RES-32K
    6. 9860
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional awareness and connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zsche
    -0.18
    ided
    -0.17
    atted
    -0.17
    ubah
    -0.17
    ange
    -0.17
    rava
    -0.17
    .SQL
    -0.17
    ains
    -0.16
    iaux
    -0.16
    enaire
    -0.16
    POSITIVE LOGITS
    lessly
    0.25
    less
    0.23
    chal
    0.18
    ful
    0.17
    fully
    0.17
     impression
    0.16
     urgency
    0.16
    folio
    0.16
     Thur
    0.16
    fulness
    0.16
    Activations Density 0.022%

    No Known Activations