© 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. 8-LLAMASCOPE-RES-32K
    11. 1964
    Prev
    Next
    INDEX
    Explanations

    various forms of words or phrases that suggest structural elements or organizational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odon
    -0.17
    ãĥ«ãĥķ
    -0.17
    oves
    -0.16
    ASY
    -0.16
    undy
    -0.15
    gre
    -0.14
    cth
    -0.14
    agher
    -0.14
    atas
    -0.14
    Assembly
    -0.14
    POSITIVE LOGITS
     огÑĢа
    0.14
     gid
    0.14
    ajo
    0.13
    ÑĪкÑĥ
    0.13
    wiÄħ
    0.13
     dál
    0.13
    bic
    0.13
     reel
    0.13
    elyn
    0.13
     Cooke
    0.12
    Activations Density 0.051%

    No Known Activations