INDEX

Explanations

phrases related to dialogue and communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ovah

-0.17

ãģĭãĤĬ

-0.16

ovan

-0.16

.serializer

-0.15

UNUSED

-0.14

anford

-0.14

rud

-0.13

ouble

-0.13

voy

-0.13

Ð»ÑİÐ±

-0.13

POSITIVE LOGITS

 have

0.22

 nothing

0.22

had

0.22

has

0.22

say

0.22

Say

0.20

 Have

0.18

 things

0.18

Have

0.18

 NOTHING

0.17

Activations Density 0.041%

phrases related to dialogue and communication

No Comments

No Known Activations