© 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. 27-LLAMASCOPE-RES-32K
    11. 12027
    Prev
    Next
    INDEX
    Explanations

    concepts related to evaluation and measurement, particularly in contexts involving value judgments and pressures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avra
    -0.15
    復
    -0.15
    bos
    -0.15
    elu
    -0.14
     ?',
    -0.14
    åIJĪ
    -0.14
    ä»ĺ
    -0.14
    reau
    -0.14
    053
    -0.14
    019
    -0.14
    POSITIVE LOGITS
     (!
    0.17
    )application
    0.17
    ë¡Ģ
    0.15
     respectively
    0.15
    ż
    0.15
    asha
    0.14
    inn
    0.14
    .weixin
    0.14
    jdbc
    0.13
    (!
    0.13
    Activations Density 0.461%

    No Known Activations