INDEX

Explanations

phrases that convey definitions or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

inus

-0.17

ekim

-0.17

readcr

-0.15

reau

-0.15

anker

-0.15

ema

-0.14

 then

-0.14

kw

-0.13

illary

-0.13

efs

-0.13

POSITIVE LOGITS

erator

0.15

istar

0.14

onis

0.14

rete

0.14

quired

0.14

earch

0.14

\Mapping

0.14

Ð´Ð¸Ð½Ð°

0.14

 Gross

0.14

äº®

0.14

Activations Density 0.043%

phrases that convey definitions or states of being

No Comments

No Known Activations