INDEX

Explanations

mentions of "things" and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

.scalablytyped

-0.20

sein

-0.18

nze

-0.17

herits

-0.16

anas

-0.15

ilk

-0.15

VERS

-0.15

seau

-0.14

isContained

-0.14

lernen

-0.14

POSITIVE LOGITS

ause

0.17

allet

0.17

İ·

0.15

aw

0.15

 Bernstein

0.15

 Getter

0.14

 Dickinson

0.14

 Rena

0.14

ç±į

0.13

ait

0.13

Activations Density 0.006%

mentions of "things" and related concepts

No Comments

No Known Activations