INDEX

Explanations

symbols or characters, particularly those that may be special or unique

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

å½

-0.15

IPS

-0.15

Ã¼s

-0.15

 ÎĶÎµ

-0.15

umpt

-0.14

marvin

-0.14

Å¾enÃŃ

-0.14

iddle

-0.14

witter

-0.14

zos

-0.14

POSITIVE LOGITS

Mic

0.21

MIC

0.18

 Mike

0.18

mic

0.18

 micron

0.17

Mic

0.17

due

0.17

skin

0.17

mik

0.17

 skin

0.17

Activations Density 0.007%

symbols or characters, particularly those that may be special or unique

No Comments

No Known Activations