© 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. 12-LLAMASCOPE-RES-32K
    11. 19839
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and health concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istan
    -0.16
    elif
    -0.15
    efe
    -0.14
    field
    -0.14
    elsea
    -0.14
    ucs
    -0.14
    Else
    -0.14
     èĩªåĬ¨çĶŁæĪIJ
    -0.13
    eted
    -0.13
    'field
    -0.13
    POSITIVE LOGITS
    ibaba
    0.16
    akeup
    0.13
    /mit
    0.13
    utely
    0.13
    PHA
    0.13
    ToDevice
    0.13
    ÃĤ
    0.13
    contents
    0.13
    anel
    0.13
    /accounts
    0.12
    Activations Density 0.125%

    No Known Activations