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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10512
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to improvement and enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    erah
    -0.17
     enough
    -0.16
    akan
    -0.15
     доÑģÑĤаÑĤоÑĩно
    -0.15
    acos
    -0.14
     доÑģÑĤаÑĤ
    -0.14
     æ¤
    -0.13
    iad
    -0.13
     доÑģиÑĤÑĮ
    -0.13
     Enough
    -0.13
    POSITIVE LOGITS
     than
    1.45
    than
    1.21
     THAN
    1.10
     Than
    1.09
    -than
    1.06
    Than
    1.06
    _than
    1.00
     niż
    0.79
     än
    0.77
     než
    0.77
    Activations Density 0.793%

    No Known Activations