© 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. 27-LLAMASCOPE-RES-32K
    6. 2885
    Prev
    Next
    INDEX
    Explanations

    references to the borough of Brooklyn

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ye
    -0.20
    y
    -0.18
    san
    -0.16
    si
    -0.16
    uv
    -0.15
    gard
    -0.15
    sWith
    -0.15
    yen
    -0.15
    sat
    -0.15
    ses
    -0.15
    POSITIVE LOGITS
    ites
    0.23
     Heights
    0.23
     Nets
    0.22
     NY
    0.22
    oklyn
    0.21
    ite
    0.21
     borough
    0.20
    ITES
    0.20
     Borough
    0.19
     Queens
    0.19
    Activations Density 0.014%

    No Known Activations