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. 13-LLAMASCOPE-RES-32K
    6. 16710
    Prev
    Next
    INDEX
    Explanations

    technical issues and troubleshooting related to forms and appliances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbo
    -0.18
    avra
    -0.17
    ilter
    -0.15
    Cool
    -0.14
    abad
    -0.14
    ARAM
    -0.14
     dangerously
    -0.14
    ourn
    -0.14
    æĶ
    -0.13
     Walter
    -0.13
    POSITIVE LOGITS
     pill
    0.19
    anford
    0.17
    IODevice
    0.15
    OMET
    0.15
    ying
    0.14
    лом
    0.14
    ires
    0.14
    pill
    0.14
    yun
    0.14
     appearing
    0.14
    Activations Density 0.275%

    No Known Activations