© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 21-LLAMASCOPE-RES-32K
    6. 8198
    Prev
    Next
    INDEX
    Explanations

    plural pronouns, particularly referencing people or subjects in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -0.28
    their
    -0.17
    ause
    -0.17
     коÑĤоÑĢое
    -0.16
    otland
    -0.16
    ä»ĸ们
    -0.16
     its
    -0.16
    its
    -0.16
     loro
    -0.15
     their
    -0.15
    POSITIVE LOGITS
    're
    0.19
    chy
    0.17
    iner
    0.17
    ’re
    0.16
    'RE
    0.15
     ÑĤакими
    0.15
    OAD
    0.15
    alic
    0.15
    kich
    0.14
    efore
    0.14
    Activations Density 0.102%

    No Known Activations