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. 28-LLAMASCOPE-RES-32K
    6. 420
    Prev
    Next
    INDEX
    Explanations

    instances of the term "interplay" or similar variations and their contextual applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enthal
    -0.16
    rage
    -0.15
    sons
    -0.15
    side
    -0.15
    sm
    -0.15
    ãģĭãģij
    -0.15
    ssi
    -0.15
    sh
    -0.15
    owie
    -0.14
    son
    -0.14
    POSITIVE LOGITS
    play
    0.24
    lop
    0.23
    locking
    0.22
     tw
    0.21
    continental
    0.20
    nees
    0.20
    lace
    0.19
     al
    0.19
    lude
    0.19
     Pret
    0.19
    Activations Density 0.019%

    No Known Activations