© 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. 15-LLAMASCOPE-RES-32K
    6. 3120
    Prev
    Next
    INDEX
    Explanations

    content and phrases related to 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 @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rine
    -0.15
    fa
    -0.15
    ault
    -0.15
    ye
    -0.14
    hey
    -0.14
    upal
    -0.14
    ή
    -0.14
    utsch
    -0.13
    .BLL
    -0.13
    adora
    -0.13
    POSITIVE LOGITS
    ãĤĩ
    0.16
    datap
    0.15
    ptrdiff
    0.14
    raison
    0.14
     loads
    0.14
     Gratuit
    0.13
    Rp
    0.13
    gnore
    0.13
    @js
    0.13
    dsp
    0.13
    Activations Density 0.384%

    No Known Activations