© 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. 19-LLAMASCOPE-RES-32K
    11. 29788
    Prev
    Next
    INDEX
    Explanations

    references to "Albion," indicating a focus on entities associated with that term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htable
    -0.19
    anas
    -0.16
    MING
    -0.15
    à¸Ĥ
    -0.14
    atrix
    -0.14
    ró
    -0.14
    gings
    -0.14
    antd
    -0.14
    valor
    -0.14
     Dumpster
    -0.14
    POSITIVE LOGITS
    querque
    0.19
    hoff
    0.18
    405
    0.18
    isme
    0.17
    right
    0.17
    inger
    0.17
    mor
    0.15
    лаб
    0.15
    ÑĢеÑħ
    0.15
    uali
    0.14
    Activations Density 0.011%

    No Known Activations