INDEX

Explanations

words related to intoxication or drunkenness

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

alue

-0.14

 JADX

-0.13

 instrumentation

-0.13

@email

-0.13

 Multip

-0.13

ULER

-0.13

Ø¨Ø±

-0.13

ä»¶

-0.13

ings

-0.13

antino

-0.13

POSITIVE LOGITS

ãģıãĤī

0.18

pike

0.17

ATAB

0.16

ards

0.16

alte

0.15

gni

0.15

.timing

0.15

atab

0.14

æĳĩ

0.14

GINE

0.14

Activations Density 0.018%

words related to intoxication or drunkenness

No Comments

No Known Activations