Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 6-LLAMASCOPE-RES-32K
    6. 28380
    Prev
    Next
    INDEX
    Explanations

    coding commands and file management instructions related to programming frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shrink
    -0.15
    ROTO
    -0.14
     PC
    -0.14
     operating
    -0.14
     ex
    -0.14
     Stick
    -0.14
     sc
    -0.14
     Globe
    -0.14
    ãĥ³ãĥĩãĤ£
    -0.14
    untime
    -0.14
    POSITIVE LOGITS
     Incontri
    0.17
    enz
    0.16
    lund
    0.16
    nnen
    0.16
    erra
    0.15
    ligt
    0.15
    ORA
    0.14
    vsp
    0.14
    riday
    0.14
     offsetof
    0.14
    Activations Density 0.401%

    No Known Activations