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. 30-LLAMASCOPE-RES-32K
    6. 23536
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structural elements in a web document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     g
    -0.17
    <|end_of_text|>
    -0.15
    –
    -0.14
    383
    -0.14
    '
    -0.14
     '
    -0.14
    ilent
    -0.14
    â̦
    -0.14
    ay
    -0.14
     Ke
    -0.14
    POSITIVE LOGITS
    >↵
    0.24
    ><
    0.21
    Uvs
    0.21
    ></
    0.18
    DMIN
    0.17
    URLException
    0.17
    ycastle
    0.17
    >↵↵
    0.16
    AILABLE
    0.16
    AXB
    0.16
    Activations Density 0.023%

    No Known Activations