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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 31-LLAMASCOPE-RES-32K
    6. 11134
    Prev
    Next
    INDEX
    Explanations

    the word "much" 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 @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slightly
    -0.16
    utomation
    -0.15
    agle
    -0.15
    haft
    -0.14
    pps
    -0.14
    unifu
    -0.14
     meget
    -0.14
    ůr
    -0.14
     exponentially
    -0.14
    oord
    -0.14
    POSITIVE LOGITS
    -needed
    0.35
     ado
    0.31
     like
    0.28
    acho
    0.28
     needed
    0.26
    needed
    0.25
     Needed
    0.25
     appreciated
    0.24
     beloved
    0.24
    -awaited
    0.23
    Activations Density 0.045%

    No Known Activations