© 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. 25-LLAMASCOPE-RES-32K
    11. 17244
    Prev
    Next
    INDEX
    Explanations

    instances of protests or movements against rights violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udder
    -0.15
    галÑĸ
    -0.14
    æľīåħ³
    -0.14
     ly
    -0.14
    MZ
    -0.13
    heimer
    -0.13
    ÙIJÙĥ
    -0.13
    डर
    -0.13
    ochen
    -0.13
     Suites
    -0.13
    POSITIVE LOGITS
     Jeg
    0.16
     بÙĩ
    0.15
    elter
    0.15
    ÙĢ
    0.15
     Pey
    0.15
    -ı
    0.14
     Persian
    0.14
    ÑĦÑĤ
    0.14
     mehr
    0.14
    .ir
    0.14
    Activations Density 0.002%

    No Known Activations