© 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. 14-LLAMASCOPE-RES-32K
    6. 13096
    Prev
    Next
    INDEX
    Explanations

    terms related to notifications and alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isle
    -0.18
    enna
    -0.15
    sta
    -0.15
     Bugs
    -0.14
     Humph
    -0.14
    017
    -0.14
    plet
    -0.14
    mmc
    -0.14
    acker
    -0.13
     Ñĩин
    -0.13
    POSITIVE LOGITS
    zilla
    0.17
    ously
    0.17
    elm
    0.16
    ingly
    0.16
    prising
    0.16
    ÏįÏĢ
    0.16
    orial
    0.16
    ting
    0.15
    ness
    0.15
    amen
    0.15
    Activations Density 0.042%

    No Known Activations