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. 16629
    Prev
    Next
    INDEX
    Explanations

    words associated with social critique and moral accountability

    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
    ittel
    -0.15
    Enumerator
    -0.15
    veis
    -0.14
    éľ
    -0.14
    -Headers
    -0.14
    è¾°
    -0.14
    rou
    -0.14
    orrect
    -0.13
    ollider
    -0.13
    persona
    -0.13
    POSITIVE LOGITS
     Perc
    0.15
     nackte
    0.14
     :::
    0.14
    447
    0.14
     Pare
    0.14
    uve
    0.14
     Kling
    0.14
    gew
    0.14
     Rudd
    0.13
     Middle
    0.13
    Activations Density 0.333%

    No Known Activations