© 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. 31-LLAMASCOPE-RES-32K
    6. 10532
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and landmarks in Cleveland

    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
     Paso
    -0.16
     Southampton
    -0.16
    ROUT
    -0.16
    Isl
    -0.15
    ãĥ
    -0.14
    edn
    -0.14
    afia
    -0.14
    одо
    -0.14
    chi
    -0.14
     NGX
    -0.14
    POSITIVE LOGITS
     Cleveland
    0.52
     Akron
    0.43
    CLE
    0.36
    leveland
    0.36
     Cavs
    0.35
     Ohio
    0.34
     Browns
    0.32
     Eu
    0.30
     NEO
    0.29
    Ak
    0.29
    Activations Density 0.078%

    No Known Activations