INDEX

Explanations

phrases that include the word "your."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

rn

-0.17

Ã³r

-0.16

iale

-0.15

é§

-0.14

aal

-0.14

 acted

-0.14

errMsg

-0.14

ni

-0.14

Orm

-0.14

vu

-0.14

POSITIVE LOGITS

cores

0.16

atorium

0.15

raquo

0.14

ansa

0.14

eut

0.14

 Haley

0.14

atinum

0.14

/-

0.14

rod

0.14

ê·Ģ

0.14

Activations Density 0.016%

phrases that include the word "your."

No Comments

No Known Activations