INDEX

Explanations

phrases indicating a level of significance or importance regarding various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

hazi

-0.17

amel

-0.14

INGS

-0.14

 basically

-0.14

ÑģÑıÑĤ

-0.14

æŁ»

-0.14

amburg

-0.14

.ibatis

-0.13

Ø²Ø§ÙĨ

-0.13

nox

-0.13

POSITIVE LOGITS

 anymore

0.32

 necessarily

0.29

nor

0.25

nor

0.18

ë§Ŀ

0.16

çĽ

0.15

Ìģc

0.15

Nor

0.15

eks

0.15

ainter

0.15

Activations Density 0.036%

phrases indicating a level of significance or importance regarding various subjects

No Comments

No Known Activations