© 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. 22250
    Prev
    Next
    INDEX
    Explanations

    emphatic statements regarding personal experiences and feelings

    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
    xico
    -0.17
    gaard
    -0.16
    iring
    -0.15
    umpt
    -0.15
    OTO
    -0.15
    адÑĥ
    -0.14
    aticon
    -0.14
    duk
    -0.13
    liest
    -0.13
    robe
    -0.13
    POSITIVE LOGITS
     trust
    0.62
     Trust
    0.55
    Trust
    0.54
    trust
    0.54
     trusts
    0.45
     believe
    0.44
     Believe
    0.43
    çĽ¸ä¿¡
    0.38
    -bel
    0.34
     belief
    0.34
    Activations Density 0.212%

    No Known Activations