INDEX

Explanations

mathematical terms and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

inja

-0.15

Ð²Ð°Ð¶Ð°

-0.15

ä»°

-0.15

ugin

-0.14

uchos

-0.14

dna

-0.14

otte

-0.14

Ã¶rt

-0.14

pij

-0.14

edido

-0.14

POSITIVE LOGITS

 Sunder

0.15

Witness

0.14

 Witness

0.13

-instagram

0.13

 Lands

0.13

 Return

0.13

 rÃµ

0.13

 though

0.13

edReader

0.13

inson

0.13

Activations Density 0.037%

mathematical terms and expressions

No Comments

No Known Activations