INDEX

Explanations

superlative terms indicating the highest degree or frequency

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

tight

-0.15

ertools

-0.14

deen

-0.14

peer

-0.13

llib

-0.13

ÃŃd

-0.13

.gdx

-0.13

uchar

-0.13

POSITIVE LOGITS

/latest

0.18

ToMany

0.15

 importantly

0.15

IVAL

0.14

ival

0.14

lon

0.14

/all

0.14

ache

0.14

ethe

0.14

Ø§ÙĬØ§

0.14

Activations Density 0.057%

superlative terms indicating the highest degree or frequency

No Comments

No Known Activations