© 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. 31-LLAMASCOPE-RES-32K
    11. 7067
    Prev
    Next
    INDEX
    Explanations

    references and instances related to specificity in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _specific
    -0.24
     specifically
    -0.23
     Specifically
    -0.22
     especÃŃf
    -0.22
    specific
    -0.22
    pecific
    -0.21
    Specific
    -0.20
     specific
    -0.19
    اÙĨÙĩ
    -0.18
     Specific
    -0.17
    POSITIVE LOGITS
    ities
    0.43
    ity
    0.40
    ially
    0.39
    ally
    0.39
    ily
    0.33
    ized
    0.30
    -purpose
    0.29
    ALLY
    0.27
    ied
    0.26
     kind
    0.25
    Activations Density 0.088%

    No Known Activations