INDEX

Explanations

phrases referring to singular entities or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

eter

-0.17

emer

-0.15

ìĦľ

-0.14

cope

-0.14

rik

-0.13

ible

-0.13

pany

-0.13

leep

-0.13

oun

-0.13

 denen

-0.13

POSITIVE LOGITS

yre

0.17

idir

0.15

ulg

0.14

amac

0.14

ughty

0.14

 Casc

0.14

ORIGINAL

0.14

æŃ¯

0.14

 Pierce

0.14

-lfs

0.14

Activations Density 0.021%

phrases referring to singular entities or concepts

No Comments

No Known Activations