© 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. 7-LLAMASCOPE-RES-32K
    11. 8095
    Prev
    Next
    INDEX
    Explanations

    references to Ukraine and its related military activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itti
    -0.17
    anine
    -0.17
    utin
    -0.16
    stadt
    -0.14
     minded
    -0.14
    coc
    -0.14
     ochran
    -0.14
    cers
    -0.14
     Ñĩа
    -0.14
     Ecc
    -0.14
    POSITIVE LOGITS
    aph
    0.15
     Pot
    0.15
    arend
    0.15
    -popup
    0.14
    iert
    0.14
    undo
    0.14
    XL
    0.14
    tz
    0.14
    neo
    0.14
    pot
    0.14
    Activations Density 0.027%

    No Known Activations