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. 18226
    Prev
    Next
    INDEX
    Explanations

    variations of the term "neutron star capture theory."

    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
    cem
    -0.16
    éal
    -0.16
    CARD
    -0.15
    ÄįnÃŃk
    -0.15
    CAST
    -0.15
    hk
    -0.15
    horn
    -0.15
    izon
    -0.15
    hod
    -0.14
    éri
    -0.14
    POSITIVE LOGITS
    ustom
    0.33
    OVID
    0.33
    ar
    0.31
    reator
    0.31
    alendar
    0.31
    entered
    0.31
    arl
    0.30
    enter
    0.30
    lose
    0.29
    arbon
    0.29
    Activations Density 0.019%

    No Known Activations