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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 18484
    Prev
    Next
    INDEX
    Explanations

    verb forms associated with aiming or directing actions

    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
    bil
    -0.14
    ancellable
    -0.14
    ighthouse
    -0.14
    ìĹŃ
    -0.14
     Wax
    -0.14
    avier
    -0.14
    á»iji
    -0.14
    è²Į
    -0.14
    rab
    -0.14
    Splash
    -0.14
    POSITIVE LOGITS
     toward
    0.25
     towards
    0.24
     hacia
    0.21
     Towards
    0.20
     directed
    0.20
    Towards
    0.19
     Tow
    0.19
    ï¼Ń
    0.18
     Aim
    0.17
    gte
    0.17
    Activations Density 0.131%

    No Known Activations