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. 16518
    Prev
    Next
    INDEX
    Explanations

    expressions related to financial performance and sales metrics

    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
    ëłµ
    -0.16
    insk
    -0.16
    aign
    -0.15
    iscopal
    -0.15
    опаÑģ
    -0.14
    ãĥ³ãĤ¸
    -0.14
    ovu
    -0.14
     æ¼Ķ
    -0.14
    imoto
    -0.14
     Conj
    -0.14
    POSITIVE LOGITS
     offset
    0.67
     compensate
    0.66
     compens
    0.66
     offsets
    0.60
    offset
    0.59
     Offset
    0.56
     compensation
    0.56
     compensated
    0.55
     OFFSET
    0.51
     Compensation
    0.51
    Activations Density 0.254%

    No Known Activations