INDEX

Explanations

references to legal jurisdictions or districts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

INGTON

-0.17

gap

-0.14

ANGED

-0.14

gap

-0.14

ington

-0.14

-gap

-0.14

cu

-0.13

ulos

-0.13

_truth

-0.13

Gap

-0.13

POSITIVE LOGITS

ffset

0.15

ixin

0.15

morgan

0.14

isclosed

0.14

Ø¨Ø§Ø²

0.14

urch

0.14

ertype

0.14

é®

0.14

ker

0.14

/io

0.14

Activations Density 0.003%

references to legal jurisdictions or districts

No Comments

No Known Activations