© 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. 24-LLAMASCOPE-RES-32K
    11. 18167
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    رÙĬب
    -0.13
    rame
    -0.13
     пÑĢеÑģÑĤ
    -0.13
    imas
    -0.13
    976
    -0.13
    ilim
    -0.13
     scrutin
    -0.13
    ernaut
    -0.12
    469
    -0.12
    ETO
    -0.12
    POSITIVE LOGITS
     leadership
    0.17
    soever
    0.14
    leaders
    0.14
     Leadership
    0.14
     winning
    0.14
     weakness
    0.14
     Lage
    0.14
     Freund
    0.14
    aser
    0.13
    Strategy
    0.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.