INDEX

Explanations

prepositions and specific phrases related to location and context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

å¤«

-0.17

irt

-0.16

å¦Ĥ

-0.15

á»ĳt

-0.15

 Bair

-0.15

uez

-0.14

VICES

-0.14

ollapse

-0.13

isphere

-0.13

 Emer

-0.13

POSITIVE LOGITS

ruk

0.17

ilan

0.16

undo

0.15

illo

0.15

ORIGINAL

0.14

VML

0.14

.DropTable

0.14

compan

0.14

achie

0.13

aptive

0.13

Activations Density 0.207%

prepositions and specific phrases related to location and context

No Comments

No Known Activations