© 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. 27-LLAMASCOPE-RES-32K
    11. 1999
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to conditions or requirements in policies or agreements

    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
    quin
    -0.16
    eras
    -0.16
    erp
    -0.15
    çĶº
    -0.15
    _strerror
    -0.15
    iniz
    -0.14
     Pax
    -0.14
     otp
    -0.14
    yer
    -0.14
    çİī
    -0.14
    POSITIVE LOGITS
    endi
    0.30
    end
    0.26
    ulation
    0.25
    ple
    0.25
    ulations
    0.24
    ends
    0.22
    ulated
    0.21
    ulate
    0.21
    pled
    0.21
    endar
    0.20
    Activations Density 0.005%

    No Known Activations