INDEX

Explanations

actions or events related to returning or going back

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ittel

-0.17

Ø§Ø¶

-0.14

ronym

-0.14

foreground

-0.14

Ľå»º

-0.13

Ľ°

-0.13

 ãĢľ

-0.13

 plÃ¡

-0.13

ponible

-0.13

Ã¡st

-0.12

POSITIVE LOGITS

 back

1.56

back

1.20

 Back

1.15

-back

1.11

Back

1.11

 BACK

1.10

_back

1.07

.back

1.01

	back

0.91

BACK

0.91

Activations Density 0.974%

actions or events related to returning or going back

No Comments

No Known Activations