INDEX

Explanations

expressions of gratitude and acknowledgment of support

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

spl

-0.14

ought

-0.14

bsp

-0.14

aga

-0.14

ev

-0.14

amba

-0.13

ever

-0.13

 hacked

-0.13

ica

-0.13

 splitter

-0.13

POSITIVE LOGITS

 ÑĦÑĥÐ½Ð´Ð°

0.19

imore

0.17

BOOLE

0.17

åĦĢ

0.17

ï»¿#

0.17

TRGL

0.16

/epl

0.16

Ð³Ð°Ð»Ñĸ

0.16

(EFFECT

0.15

senal

0.15

Activations Density 0.615%

expressions of gratitude and acknowledgment of support

No Comments

No Known Activations