© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 6-LLAMASCOPE-RES-32K
    6. 5890
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to satire and sarcasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erras
    -0.16
    arine
    -0.16
    angent
    -0.15
    ango
    -0.15
     bud
    -0.14
     sensit
    -0.14
    tah
    -0.14
    @Id
    -0.14
     melod
    -0.14
    mania
    -0.14
    POSITIVE LOGITS
    šak
    0.15
    .func
    0.15
    ivor
    0.15
    infeld
    0.15
    ase
    0.15
    cce
    0.14
    деÑĤ
    0.14
     Kra
    0.14
    uish
    0.14
    orld
    0.14
    Activations Density 0.079%

    No Known Activations