INDEX

Explanations

conjunctions and phrases that indicate relationships or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ogan

-0.20

plen

-0.18

uben

-0.15

NOP

-0.15

etten

-0.15

 Kane

-0.14

ÑĢÑİ

-0.14

å¨ľ

-0.14

uen

-0.14

ivet

-0.14

POSITIVE LOGITS

esa

0.18

zie

0.16

 áº¥n

0.15

xED

0.15

yr

0.15

RL

0.15

olly

0.14

ech

0.14

çĲ´

0.14

vs

0.14

Activations Density 0.085%

conjunctions and phrases that indicate relationships or conditions

No Comments

No Known Activations