© 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. 10-LLAMASCOPE-RES-32K
    11. 29764
    Prev
    Next
    INDEX
    Explanations

    statements regarding the necessity and benefits of hiring legal or professional assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brig
    -0.17
    ctl
    -0.16
     Conte
    -0.16
    atic
    -0.15
    uti
    -0.15
    ancements
    -0.15
    usz
    -0.15
    tsky
    -0.15
    bah
    -0.14
    anche
    -0.14
    POSITIVE LOGITS
    _REQUIRED
    0.14
    [arg
    0.14
    odom
    0.14
    å¥Ĺ
    0.14
    adge
    0.14
    argout
    0.13
     Fleming
    0.13
    quito
    0.13
     Horse
    0.13
    assi
    0.13
    Activations Density 0.356%

    No Known Activations