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. 31-LLAMASCOPE-RES-32K
    6. 9971
    Prev
    Next
    INDEX
    Explanations

    themes related to identity and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     To
    -0.15
     since
    -0.14
     Of
    -0.14
    -To
    -0.14
     à¤ľà¤¬à¤ķ
    -0.14
     whereas
    -0.13
     although
    -0.13
    -Man
    -0.13
    ToPoint
    -0.13
     And
    -0.13
    POSITIVE LOGITS
     Your
    0.38
     Those
    0.35
     Their
    0.35
     These
    0.35
     Each
    0.34
     Our
    0.32
     Some
    0.31
    Your
    0.30
     Various
    0.30
     Several
    0.28
    Activations Density 0.268%

    No Known Activations