© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 11107
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "is" and related statements that establish identity or definition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plusplus
    -0.16
    ropoda
    -0.16
     sứ
    -0.16
    знаÑĩ
    -0.14
    agedList
    -0.14
    .cloudflare
    -0.14
    lernen
    -0.13
    aliz
    -0.13
    SqlConnection
    -0.13
    Ĵ
    -0.13
    POSITIVE LOGITS
     called
    0.90
    called
    0.78
     Called
    0.74
    Called
    0.66
    -called
    0.59
     termed
    0.59
    åı«
    0.57
     llam
    0.53
    ç§°
    0.52
     named
    0.49
    Activations Density 0.002%

    No Known Activations