INDEX

Explanations

references to coffee and related products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ob

-0.17

soever

-0.15

urally

-0.15

PARATOR

-0.14

PAS

-0.14

ship

-0.14

hum

-0.14

.stem

-0.14

ed

-0.14

 conn

-0.13

POSITIVE LOGITS

zimmer

0.17

amaz

0.17

abbage

0.16

rippling

0.15

 Relief

0.15

fea

0.15

presso

0.15

anova

0.14

zia

0.14

udev

0.14

Activations Density 0.011%

references to coffee and related products

No Comments

No Known Activations