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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 18550
    Prev
    Next
    INDEX
    Explanations

    references to community involvement and support systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¤ij
    -0.14
    بÙĪر
    -0.14
    aji
    -0.14
    aad
    -0.14
    rug
    -0.14
    .processor
    -0.13
    elin
    -0.13
    าะ
    -0.13
    CanBe
    -0.13
    can
    -0.13
    POSITIVE LOGITS
     believe
    0.26
     belief
    0.25
     recognizes
    0.23
     believes
    0.22
     beliefs
    0.21
     recognize
    0.21
    recogn
    0.21
     value
    0.21
     believing
    0.21
    _bel
    0.21
    Activations Density 0.189%

    No Known Activations