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. 30-LLAMASCOPE-RES-32K
    6. 21483
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and recognition for individuals who have made a significant impact in their fields

    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
    ander
    -0.18
    prü
    -0.15
    opoulos
    -0.14
    ucci
    -0.14
    uko
    -0.13
    phia
    -0.13
    elocity
    -0.13
    prung
    -0.13
     Previously
    -0.13
    ëŀij
    -0.13
    POSITIVE LOGITS
     unst
    0.24
     warmth
    0.20
     colleg
    0.19
     warm
    0.19
     always
    0.19
     quiet
    0.18
     tire
    0.18
    always
    0.18
    warm
    0.18
    Always
    0.17
    Activations Density 0.087%

    No Known Activations