© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 3365
    Prev
    Next
    INDEX
    Explanations

    negatively charged emotions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unter
    -0.22
    K
    -0.20
    s
    -0.19
    Ñı
    -0.19
    qu
    -0.19
    INFRINGEMENT
    -0.18
    A
    -0.18
    Ðľ
    -0.18
    L
    -0.18
    an
    -0.18
    POSITIVE LOGITS
    /-
    0.20
    rc
    0.18
    /+
    0.18
    weather
    0.17
    voice
    0.16
    =-=-=-=-=-=-=-=-
    0.16
    ness
    0.16
    _-
    0.16
    vest
    0.15
    =-=-=-=-
    0.15
    Activations Density 0.248%

    No Known Activations