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. 24-LLAMASCOPE-RES-32K
    6. 7849
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gross
    -0.15
     genders
    -0.15
    gender
    -0.15
     Cunning
    -0.15
    fragistics
    -0.15
    ê³¼ìłķ
    -0.14
    zee
    -0.14
     cris
    -0.14
    ÏĦοÏħ
    -0.14
    å¤
    -0.14
    POSITIVE LOGITS
    (G
    0.19
    /G
    0.17
    EDIA
    0.15
    (GL
    0.15
    .GL
    0.15
    =G
    0.14
    .son
    0.14
    LOCKS
    0.14
    /GL
    0.14
     g
    0.14
    Activations Density 0.227%

    No Known Activations