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. 28-LLAMASCOPE-RES-32K
    6. 30847
    Prev
    Next
    INDEX
    Explanations

    references to architectural elements and cultural heritage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    áng
    -0.17
    jack
    -0.16
     BAÅŀ
    -0.15
    rof
    -0.15
     statues
    -0.15
    Äĥn
    -0.15
    anni
    -0.15
    _GUI
    -0.14
    $LANG
    -0.14
    taire
    -0.14
    POSITIVE LOGITS
     Hag
    0.23
    mos
    0.23
    Mos
    0.22
     Mos
    0.20
     mos
    0.20
     hare
    0.20
     hamm
    0.20
     Friday
    0.20
     Fat
    0.19
     rug
    0.19
    Activations Density 0.042%

    No Known Activations