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. 18-LLAMASCOPE-RES-32K
    6. 16592
    Prev
    Next
    INDEX
    Explanations

    references to outdated or unsupported technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifr
    -0.15
    âĦĸâĦĸ
    -0.14
    elay
    -0.14
     forthcoming
    -0.13
    ajor
    -0.13
    ORA
    -0.13
     пÑĥÑģÑĤ
    -0.13
     delayed
    -0.13
    away
    -0.12
     normally
    -0.12
    POSITIVE LOGITS
     old
    0.52
     older
    0.51
     outdated
    0.47
    -old
    0.42
     OLD
    0.41
     Older
    0.40
     obsolete
    0.40
    (old
    0.40
    _old
    0.38
    older
    0.38
    Activations Density 0.282%

    No Known Activations