INDEX

Explanations

culinary terms and ingredient descriptors

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

etÃŃ

-0.16

keiten

-0.15

oty

-0.15

æĮĤ

-0.14

eck

-0.14

ãģĭãĤĬ

-0.14

istration

-0.14

 Predictor

-0.14

Ð½Ð¸ÑĩÐµÑģ

-0.14

POSITIVE LOGITS

df

0.17

ÎĲ

0.17

 unreachable

0.16

 Davis

0.15

 Holl

0.15

aux

0.14

 unfortunately

0.14

 Tone

0.14

GGLE

0.14

odont

0.14

Activations Density 0.170%

culinary terms and ingredient descriptors

No Comments

No Known Activations