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. 10234
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that" and variations of its usage in sentences

    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
     and
    -0.29
    	and
    -0.18
     or
    -0.18
    and
    -0.18
    ãģĤãĤĭ
    -0.17
    (
    -0.16
    (and
    -0.16
     и
    -0.16
    them
    -0.15
    him
    -0.15
    POSITIVE LOGITS
     nobody
    0.34
    'll
    0.34
     many
    0.31
     everyone
    0.31
    ’ll
    0.30
     you
    0.29
    's
    0.28
     few
    0.28
     anyone
    0.28
     everybody
    0.27
    Activations Density 0.287%

    No Known Activations