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. 2075
    Prev
    Next
    INDEX
    Explanations

    descriptors that assess quality or condition

    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
    ynos
    -0.17
    omba
    -0.17
     Kad
    -0.15
    ottage
    -0.15
    af
    -0.15
     minds
    -0.14
    azio
    -0.14
    еÑĪÑĮ
    -0.14
     Hogan
    -0.14
     eb
    -0.14
    POSITIVE LOGITS
    261
    0.18
    713
    0.15
    ANI
    0.15
    èĪĮ
    0.15
    edBy
    0.15
    ogue
    0.15
    229
    0.14
     now
    0.14
     Quarter
    0.14
    Quarter
    0.14
    Activations Density 1.275%

    No Known Activations