Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 21-LLAMASCOPE-RES-32K
    6. 16461
    Prev
    Next
    INDEX
    Explanations

    references to organizations or clubs and their establishment history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atement
    -0.14
     Obr
    -0.14
    ittel
    -0.14
    istributed
    -0.13
    vrd
    -0.13
    edic
    -0.13
    ardon
    -0.13
    ammen
    -0.13
     æľŁ
    -0.13
    енÑı
    -0.13
    POSITIVE LOGITS
     founded
    0.52
     Founded
    0.44
     formed
    0.44
     formation
    0.42
     established
    0.42
    Founded
    0.42
    æĪIJç«ĭ
    0.39
    establish
    0.39
     establishment
    0.39
     Established
    0.38
    Activations Density 0.231%

    No Known Activations