INDEX

Explanations

phrases that express similarity or comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

.UnitTesting

-0.17

nya

-0.17

lio

-0.16

nist

-0.16

_ASSUME

-0.15

roe

-0.15

agon

-0.15

Ð»ÑĥÐ³

-0.15

self

-0.15

ponent

-0.15

POSITIVE LOGITS

-minded

0.19

elihood

0.18

æł·çļĦ

0.17

HeaderValue

0.17

 never

0.16

 unto

0.16

-kind

0.16

 minded

0.15

able

0.15

WISE

0.15

Activations Density 0.095%

phrases that express similarity or comparison

No Comments

No Known Activations