Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 17601
    Prev
    Next
    INDEX
    Explanations

    references to formal documentation and records related to death and census data

    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
    лÑĥж
    -0.15
     Eigen
    -0.15
    Eigen
    -0.14
     unary
    -0.14
    apel
    -0.14
     Morav
    -0.14
     Bedford
    -0.14
     surveys
    -0.13
     بÙĪØ§Ø¨Ø©
    -0.13
    getLast
    -0.13
    POSITIVE LOGITS
     micro
    0.20
     Micro
    0.19
    micro
    0.18
    _micro
    0.18
    Micro
    0.18
     roll
    0.16
     Roll
    0.15
    cki
    0.15
     Film
    0.15
    film
    0.15
    Activations Density 0.013%

    No Known Activations