© 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. 11-LLAMASCOPE-RES-32K
    11. 30191
    Prev
    Next
    INDEX
    Explanations

    references to individuals affected by mental health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avr
    -0.15
    ceph
    -0.15
    è·
    -0.14
    regn
    -0.14
    lington
    -0.14
    izo
    -0.14
    rax
    -0.14
    vida
    -0.14
    eneg
    -0.13
    awn
    -0.13
    POSITIVE LOGITS
    hip
    0.14
    ago
    0.14
    773
    0.14
     uncomp
    0.14
    ail
    0.13
    uelles
    0.13
     pelo
    0.13
    ael
    0.13
    erve
    0.13
     Cro
    0.13
    Activations Density 0.033%

    No Known Activations