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. 15-LLAMASCOPE-RES-32K
    6. 5628
    Prev
    Next
    INDEX
    Explanations

    terms related to ergonomics and its principles

    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
    ãĥ¼ãĥĬ
    -0.14
    iesen
    -0.13
    aphrag
    -0.13
    omm
    -0.13
    vak
    -0.13
    Ñģен
    -0.13
     doz
    -0.13
    ilim
    -0.13
    igy
    -0.13
    ounder
    -0.13
    POSITIVE LOGITS
    æİī
    0.15
     pros
    0.15
    anson
    0.14
    asso
    0.14
    ¯
    0.14
    abil
    0.14
     Vs
    0.13
    ffect
    0.13
    javax
    0.13
     eldre
    0.13
    Activations Density 0.140%

    No Known Activations