© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 11467
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to LGBT rights and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mlink
    -0.15
    _ABI
    -0.15
    ADIO
    -0.15
    ãĥ¡ãĥ©
    -0.14
    laps
    -0.14
    nat
    -0.14
     åĿ
    -0.14
    .XR
    -0.14
    gui
    -0.13
     trainable
    -0.13
    POSITIVE LOGITS
     gay
    0.62
     queer
    0.54
     Gay
    0.54
     LGBT
    0.53
    gay
    0.52
     LGBTQ
    0.50
    Gay
    0.49
     lesbian
    0.47
     homosexual
    0.46
    -gay
    0.46
    Activations Density 0.501%

    No Known Activations