© 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. 18351
    Prev
    Next
    INDEX
    Explanations

    significant events related to organizational changes and community involvement

    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
    ibraries
    -0.13
    ãĥ¬ãĥĥãĥĪ
    -0.13
    ddd
    -0.12
     unidentified
    -0.11
    deen
    -0.11
    inho
    -0.11
     Ø®ÙĪدش
    -0.11
    .EventType
    -0.11
    Âł
    -0.11
    nbsp
    -0.11
    POSITIVE LOGITS
    vou
    0.17
    iterr
    0.16
    oulos
    0.15
    olit
    0.15
    GenerationStrategy
    0.15
    olie
    0.15
    chwitz
    0.15
    GuidId
    0.14
     Hlav
    0.14
    antor
    0.13
    Activations Density 0.301%

    No Known Activations