© 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. 14-LLAMASCOPE-RES-32K
    11. 12875
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /stdc
    -0.19
    otto
    -0.16
    STANCE
    -0.15
    owy
    -0.14
    ogi
    -0.14
    ideon
    -0.14
    .DefaultCellStyle
    -0.14
    /load
    -0.13
    swick
    -0.13
    ä»ķ
    -0.13
    POSITIVE LOGITS
     imagination
    0.16
    lar
    0.14
    agraph
    0.14
    oyo
    0.13
     Grace
    0.13
    ä¸ĢçĤ¹
    0.13
    oa
    0.13
    _FC
    0.13
    agination
    0.13
     dormant
    0.13
    Activations Density 0.110%

    No Known Activations