INDEX

Explanations

phrases advocating for or against specific actions and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ÏĦÎ¹Î±

-0.17

unsch

-0.16

esch

-0.16

illet

-0.16

èĭĹ

-0.15

ieties

-0.15

 moduleName

-0.14

etten

-0.14

adele

-0.14

Ã¹i

-0.14

POSITIVE LOGITS

areth

0.18

ucz

0.16

.Framework

0.16

angu

0.15

 Leer

0.14

_SKIP

0.14

å¢ĵ

0.14

 Bened

0.14

imin

0.14

Activations Density 0.098%

phrases advocating for or against specific actions and decisions

No Comments

No Known Activations