INDEX

Explanations

mentions of character encoding formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

oo

-0.17

 ustanov

-0.16

exion

-0.16

ele

-0.15

edException

-0.15

iram

-0.15

edList

-0.15

ellen

-0.14

-pdf

-0.14

ì¶ķ

-0.14

POSITIVE LOGITS

0.18

 characters

0.15

McB

0.14

CDATA

0.14

 æ¹

0.14

taÅŁ

0.14

Encode

0.14

atter

0.14

.GetBytes

0.14

Activations Density 0.003%

mentions of character encoding formats

No Comments

No Known Activations