INDEX

Explanations

references to regulatory bodies and commission-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ongan

-0.17

_refl

-0.16

ifu

-0.16

iken

-0.15

æ¯į

-0.14

áº¥n

-0.14

thood

-0.14

Î¸Î¹

-0.14

åĿĬ

-0.14

ve

-0.14

POSITIVE LOGITS

rek

0.16

erate

0.16

aya

0.15

aye

0.15

obot

0.15

ÅĻ

0.14

errupt

0.14

roj

0.14

£¼

0.14

rud

0.14

Activations Density 0.020%

references to regulatory bodies and commission-related terms

No Comments

No Known Activations