© 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. 23-LLAMASCOPE-RES-32K
    11. 289
    Prev
    Next
    INDEX
    Explanations

    references to general plural nouns indicating people or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĦãĤĭ
    -0.30
    ãģĦãģŁ
    -0.28
    ————————————————
    -0.21
    ت
    -0.21
    ————————
    -0.20
    ated
    -0.19
    ————
    -0.18
    ample
    -0.18
    ะ
    -0.17
    aphore
    -0.17
    POSITIVE LOGITS
    ร
    0.31
    न
    0.27
    ìĦľëĬĶ
    0.25
    iy
    0.24
    ìĦľ
    0.20
    iw
    0.20
    ment
    0.19
    Ùħ
    0.19
    ãģªãģĦ
    0.18
    acon
    0.18
    Activations Density 0.448%

    No Known Activations