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. 1860
    Prev
    Next
    INDEX
    Explanations

    specific instances of the letter "F" 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
    enburg
    -0.18
    ensity
    -0.16
    328
    -0.15
    živ
    -0.15
    ively
    -0.15
    uckle
    -0.15
    Pu
    -0.15
    engers
    -0.14
     ves
    -0.14
    .throw
    -0.14
    POSITIVE LOGITS
    oi
    0.31
    az
    0.25
    ato
    0.24
    ale
    0.24
    izer
    0.23
    atur
    0.23
    azer
    0.23
    ator
    0.22
    echo
    0.21
    ogo
    0.21
    Activations Density 0.005%

    No Known Activations