INDEX

Explanations

expressions that convey judgement or assumptions about actions and situations

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

odyn

-0.16

ihan

-0.16

croft

-0.15

TEE

-0.15

tiv

-0.15

jom

-0.14

ombre

-0.14

zte

-0.14

worth

-0.14

asio

-0.14

POSITIVE LOGITS

bine

0.18

 ç¢

0.15

oni

0.15

defaults

0.15

elez

0.15

0.14

avis

0.14

icz

0.14

 blockSize

0.14

Activations Density 0.007%

expressions that convey judgement or assumptions about actions and situations

No Comments

No Known Activations