© 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. 25-LLAMASCOPE-RES-32K
    11. 22368
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Der" and its variations, which are indicative of references to titles or names in German contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igkeit
    -0.16
    taire
    -0.15
    ATUS
    -0.15
    alled
    -0.15
     è¾
    -0.15
    ãĥ£
    -0.15
    stown
    -0.15
    lover
    -0.15
    runner
    -0.15
    yr
    -0.15
    POSITIVE LOGITS
    anged
    0.27
    ivative
    0.24
    angement
    0.24
    ksen
    0.21
    went
    0.20
    neÄŁi
    0.20
    ivation
    0.19
    ivery
    0.19
    wish
    0.19
    udder
    0.17
    Activations Density 0.014%

    No Known Activations