© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 17895
    Prev
    Next
    INDEX
    Explanations

    mentions of controversial topics or discussions

    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
    ãĥ«ãĤ¯
    -0.16
    warts
    -0.14
    urally
    -0.14
    aravel
    -0.14
    addtogroup
    -0.13
     kola
    -0.13
    izoph
    -0.13
    Advertisements
    -0.13
    QRST
    -0.13
    ernote
    -0.13
    POSITIVE LOGITS
     Twitter
    0.30
     online
    0.30
     social
    0.28
     twitter
    0.27
     users
    0.25
     twe
    0.25
     reactions
    0.25
     tweets
    0.24
     posts
    0.24
     responses
    0.24
    Activations Density 0.173%

    No Known Activations