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. 21-LLAMASCOPE-RES-32K
    6. 15582
    Prev
    Next
    INDEX
    Explanations

    names and references related to a specific person or organization

    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
    ITHER
    -0.15
     filib
    -0.14
    ither
    -0.14
    locker
    -0.14
    íĭ±
    -0.14
    ç«¥
    -0.14
    aes
    -0.14
    å½ķ
    -0.14
    ADING
    -0.14
     Microsystems
    -0.14
    POSITIVE LOGITS
    resse
    0.17
    eyle
    0.17
    osg
    0.17
    ride
    0.16
    eye
    0.15
    jes
    0.15
    ught
    0.15
    eter
    0.15
    Fra
    0.15
    emat
    0.15
    Activations Density 0.019%

    No Known Activations