INDEX

Explanations

regular expression patterns in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ptal

-0.18

ython

-0.16

">ÃĹ</

-0.14

cxx

-0.14

yll

-0.14

edm

-0.14

à¸¥à¸²à¸¢

-0.13

ional

-0.13

.Cons

-0.13

geist

-0.13

POSITIVE LOGITS

 Plugin

0.20

 undef

0.20

plugin

0.18

 Centre

0.18

 plugin

0.18

_perf

0.18

pod

0.17

perf

0.17

 perf

0.17

Plugin

0.16

Activations Density 0.000%

regular expression patterns in text

No Comments

No Known Activations