INDEX

Explanations

references to specific individuals or entities, possibly in a cultural or artistic context

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

mys

-0.16

.Generated

-0.15

ienes

-0.15

Å¯r

-0.15

_hint

-0.15

ieres

-0.14

riere

-0.14

½

-0.14

ckt

-0.14

zÄħ

-0.14

POSITIVE LOGITS

ovic

0.30

iÄĩ

0.24

ic

0.23

ivic

0.22

Äĩ

0.22

olic

0.22

acic

0.21

Äĳ

0.21

 Milo

0.20

usic

0.20

Activations Density 0.026%

references to specific individuals or entities, possibly in a cultural or artistic context

No Comments

No Known Activations