© 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. 19320
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to job applications and formal requirements in professional settings

    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
    aversable
    -0.16
    chez
    -0.15
    hea
    -0.15
    ħn
    -0.15
    HA
    -0.15
    ellido
    -0.14
    icmp
    -0.14
    itespace
    -0.14
     UNU
    -0.14
    LOPT
    -0.14
    POSITIVE LOGITS
    inars
    0.18
    IGHL
    0.16
    throat
    0.16
     overhead
    0.15
    .disc
    0.15
    ByName
    0.15
    acr
    0.14
    ToBounds
    0.14
    875
    0.14
    owo
    0.14
    Activations Density 0.015%

    No Known Activations