© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 11450
    Prev
    Next
    INDEX
    Explanations

    references to financial data and market performance indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quant
    -0.15
     huy
    -0.15
    umer
    -0.14
     slap
    -0.14
     Quant
    -0.14
     quantitative
    -0.14
    NSURLSession
    -0.14
    ype
    -0.14
    象
    -0.14
     statistical
    -0.14
    POSITIVE LOGITS
     weights
    0.23
    Smooth
    0.21
    Weights
    0.20
     smoothing
    0.20
    smooth
    0.20
     lag
    0.19
     smoothed
    0.19
    weights
    0.19
    weight
    0.18
     proxy
    0.18
    Activations Density 0.079%

    No Known Activations