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. 13-LLAMASCOPE-RES-32K
    6. 15436
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĤãĤĭ
    -0.18
    Ùĩ
    -0.17
    ãģĤãģ£ãģŁ
    -0.16
    ãģĤãĤĬ
    -0.15
    sad
    -0.15
    ised
    -0.15
    nop
    -0.15
    lems
    -0.14
    plate
    -0.14
    sms
    -0.14
    POSITIVE LOGITS
    /th
    0.26
    ched
    0.26
    chy
    0.20
    -ÑĤо
    0.20
    ching
    0.20
     же
    0.19
     same
    0.19
    abouts
    0.18
    aways
    0.18
    iner
    0.17
    Activations Density 0.152%

    No Known Activations