INDEX

Explanations

goals related to achievement

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

eba

-0.16

aking

-0.15

aty

-0.15

nge

-0.15

ality

-0.15

/OR

-0.14

.Unity

-0.14

tery

-0.14

uddy

-0.14

iers

-0.14

POSITIVE LOGITS

ments

0.17

TRGL

0.16

ment

0.15

ieves

0.15

ieve

0.14

andro

0.14

LOAT

0.14

asar

0.14

eson

0.14

yonel

0.14

Activations Density 0.034%

goals related to achievement

No Comments

No Known Activations