© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 3-LLAMASCOPE-RES-32K
    11. 16665
    Prev
    Next
    INDEX
    Explanations

    negative expressions related to disappointment or discontent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chaft
    -0.15
    гÑĢа
    -0.14
     disc
    -0.14
    ]={↵
    -0.14
     McGr
    -0.13
     Agent
    -0.13
    ucci
    -0.13
    ality
    -0.13
     complement
    -0.13
    ereal
    -0.13
    POSITIVE LOGITS
    inet
    0.17
    .azure
    0.17
    457
    0.15
    ød
    0.15
    lish
    0.14
    edException
    0.14
    /flutter
    0.13
    овÑĸ
    0.13
    ardy
    0.13
    pret
    0.13
    Activations Density 0.013%

    No Known Activations