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. 16929
    Prev
    Next
    INDEX
    Explanations

    themes related to cultural knowledge preservation and institutional values

    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
    ìĭłì²Ń
    -0.14
     áreas
    -0.13
    ìļ©
    -0.13
    æ£
    -0.13
    สà¸Ļ
    -0.13
    éĩĬ
    -0.12
     remot
    -0.12
    vailability
    -0.12
    again
    -0.12
    oproject
    -0.12
    POSITIVE LOGITS
     preserved
    0.25
     maintained
    0.21
     preservation
    0.20
     preserving
    0.20
     preserve
    0.20
     centuries
    0.20
     decades
    0.18
     heritage
    0.18
     within
    0.18
     intact
    0.17
    Activations Density 0.126%

    No Known Activations