INDEX

Explanations

operations related to joining, splitting, and manipulating strings or arrays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Ã³Å¼

-0.16

ÐĶÐļ

-0.15

eral

-0.15

phasis

-0.15

«ĺ

-0.15

ÐµÑģÐ¸

-0.14

ÑĭÐ¿

-0.14

peria

-0.14

asia

-0.14

anst

-0.14

POSITIVE LOGITS

 Ellis

0.15

 Compound

0.15

lim

0.15

 compounds

0.15

 compound

0.14

lam

0.14

 Ward

0.14

 Webb

0.14

Lam

0.14

eward

0.14

Activations Density 0.021%

operations related to joining, splitting, and manipulating strings or arrays

No Comments

No Known Activations