INDEX

Explanations

fragments of code related to processing requests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

_FILENO

-0.16

vit

-0.15

resse

-0.15

 THREAD

-0.15

AMPLE

-0.15

à¤¿à¤¯à¤¤

-0.14

erv

-0.14

 Trident

-0.14

iday

-0.14

ervas

-0.14

POSITIVE LOGITS

 foreach

0.22

	foreach

0.20

0.19

foreach

0.19

Hab

0.15

edback

0.15

($

0.15

$this

0.15

loquent

0.15

rox

0.15

Activations Density 0.019%

fragments of code related to processing requests

No Comments

No Known Activations