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. 11288
    Prev
    Next
    INDEX
    Explanations

    terms related to legislation and societal issues

    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
    /Branch
    -0.30
    /Base
    -0.24
    Barrier
    -0.23
     Batch
    -0.23
     Bip
    -0.23
    Batch
    -0.23
    BITS
    -0.23
    Bounding
    -0.23
    BIT
    -0.22
     Bash
    -0.22
    POSITIVE LOGITS
    -b
    0.65
    Âłb
    0.53
    _b
    0.51
    -B
    0.47
    	b
    0.44
    .b
    0.40
    _B
    0.40
     ब
    0.37
    .B
    0.35
    ÂłB
    0.35
    Activations Density 1.204%

    No Known Activations