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. 15-LLAMASCOPE-RES-32K
    6. 9411
    Prev
    Next
    INDEX
    Explanations

    instances of the word "subscribe."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obl
    -0.17
    uli
    -0.16
    uly
    -0.15
    ninger
    -0.15
    elin
    -0.15
    sten
    -0.15
    ads
    -0.14
    аÑĤо
    -0.14
    umann
    -0.14
    ches
    -0.14
    POSITIVE LOGITS
    .unsubscribe
    0.19
    allee
    0.16
    .fd
    0.15
    ivate
    0.15
    ¢åįķ
    0.14
    affles
    0.14
    ÑĥÑģ
    0.14
    iT
    0.14
    _userdata
    0.14
    =sub
    0.13
    Activations Density 0.008%

    No Known Activations