© 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. 18-LLAMASCOPE-RES-32K
    6. 5981
    Prev
    Next
    INDEX
    Explanations

    the pronoun "I" and variations of it, indicating a focus on personal experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cco
    -0.15
    ÙĨز
    -0.14
    cca
    -0.14
    nech
    -0.14
    mont
    -0.14
    /Application
    -0.13
    icher
    -0.13
    avenport
    -0.13
    O
    -0.13
     comm
    -0.13
    POSITIVE LOGITS
    ogui
    0.17
    ustum
    0.15
     Cant
    0.15
    anni
    0.15
    itals
    0.15
    .gwt
    0.15
     consent
    0.14
    ÙĪØŃ
    0.14
    cion
    0.14
    368
    0.14
    Activations Density 0.181%

    No Known Activations