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. 5-LLAMASCOPE-RES-32K
    6. 211
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to fonts and typography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    'gc
    -0.18
    лÑİд
    -0.15
    coles
    -0.15
    ÐķС
    -0.14
    ÃŃsto
    -0.14
    ificate
    -0.14
     Чи
    -0.14
    .labelX
    -0.14
    visa
    -0.14
    ifo
    -0.14
    POSITIVE LOGITS
    agli
    0.16
     fet
    0.14
    ogr
    0.14
    aji
    0.14
     Vander
    0.14
    roc
    0.14
    itable
    0.14
    ries
    0.14
    Extended
    0.14
     Jaw
    0.13
    Activations Density 0.031%

    No Known Activations