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. 30-LLAMASCOPE-RES-32K
    6. 11488
    Prev
    Next
    INDEX
    Explanations

    references to significant quantities and measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    βολ
    -0.16
    TypeInfo
    -0.15
    Henry
    -0.15
    roof
    -0.15
     Solic
    -0.14
    ÑĢÑĥб
    -0.14
    _traits
    -0.14
    wdx
    -0.14
    emons
    -0.14
    ittings
    -0.14
    POSITIVE LOGITS
    acers
    0.16
    ernet
    0.16
    áp
    0.15
    raith
    0.15
    rij
    0.14
    TV
    0.14
    po
    0.14
    ay
    0.14
     Bij
    0.14
    æŃ
    0.14
    Activations Density 0.016%

    No Known Activations