Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 18831
    Prev
    Next
    INDEX
    Explanations

    phrases related to fitness equipment and its features

    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
    ìĶ
    -0.17
    ware
    -0.14
    ÑĤик
    -0.14
     Feder
    -0.14
     enqu
    -0.14
     Gross
    -0.14
    ões
    -0.14
    ailer
    -0.13
    çĨ
    -0.13
    .Dispatch
    -0.13
    POSITIVE LOGITS
     resistance
    0.27
     Resistance
    0.25
     dumb
    0.23
    Resistance
    0.23
     machine
    0.20
     tread
    0.19
     ped
    0.18
    .machine
    0.18
     row
    0.18
     machines
    0.18
    Activations Density 0.265%

    No Known Activations