© 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. 10-LLAMASCOPE-RES-32K
    11. 20830
    Prev
    Next
    INDEX
    Explanations

    references to environmental hazards and incidents involving animals and human remains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnderTest
    -0.18
    shell
    -0.15
    ction
    -0.14
    aise
    -0.14
    ÑģÑı
    -0.14
    éĹ´
    -0.14
    chsel
    -0.14
    .appspot
    -0.14
    vang
    -0.13
    _ASSUME
    -0.13
    POSITIVE LOGITS
    ecimal
    0.16
    леÑĩ
    0.15
    CLUDING
    0.15
    roj
    0.14
    orer
    0.14
    ares
    0.14
    Matches
    0.14
    é½IJ
    0.14
     Matches
    0.14
    ãi
    0.14
    Activations Density 0.234%

    No Known Activations