© 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. 4-LLAMASCOPE-RES-32K
    11. 14887
    Prev
    Next
    INDEX
    Explanations

    terms related to prostitution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    errupted
    -0.17
    ÏĨÏħ
    -0.17
     киÑģ
    -0.14
    387
    -0.14
    átor
    -0.14
    isters
    -0.14
    dÃŃ
    -0.14
    享
    -0.13
     Pompe
    -0.13
    bao
    -0.13
    POSITIVE LOGITS
    ulas
    0.15
    ãĥ¼ãĥ©
    0.14
    ifer
    0.14
    abytes
    0.14
    onga
    0.13
    SENSOR
    0.13
    etas
    0.13
    ngo
    0.13
    oti
    0.13
     DF
    0.13
    Activations Density 0.009%

    No Known Activations