© 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. 29550
    Prev
    Next
    INDEX
    Explanations

    references to attacks and their impacts, particularly involving victims and military actions

    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
    igs
    -0.15
    opoulos
    -0.15
    UF
    -0.15
    uft
    -0.14
    ç·
    -0.14
    onda
    -0.14
    iegel
    -0.14
     HI
    -0.13
    fol
    -0.13
    zia
    -0.13
    POSITIVE LOGITS
    berman
    0.16
    ÑĢеÑĪ
    0.15
    usercontent
    0.15
     jich
    0.13
    eer
    0.13
    LETED
    0.13
    PixelFormat
    0.13
    ÄĽr
    0.13
    /title
    0.13
    ASSERT
    0.13
    Activations Density 0.135%

    No Known Activations