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. 14-LLAMASCOPE-RES-32K
    6. 12458
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and conditions related to functions and their convergence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    387
    -0.19
    oulos
    -0.16
    osy
    -0.15
    бÑĥ
    -0.14
    isms
    -0.14
     vår
    -0.14
    _SUITE
    -0.14
    ach
    -0.14
    ic
    -0.14
     chÃŃ
    -0.13
    POSITIVE LOGITS
    sz
    0.15
    arella
    0.15
     contempor
    0.15
    .gmail
    0.14
    CAC
    0.14
     Pey
    0.14
    ssc
    0.14
    etler
    0.14
    å¾Ĵ
    0.14
    Ñĩай
    0.14
    Activations Density 0.104%

    No Known Activations