INDEX

Explanations

references to actions related to purchasing and acquiring items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

iones

-0.16

ye

-0.15

jen

-0.15

AW

-0.15

je

-0.14

ized

-0.14

ion

-0.14

ica

-0.14

ively

-0.14

POSITIVE LOGITS

Ø§Ø±Ø§ÙĨ

0.19

buy

0.18

/license

0.18

outs

0.17

enance

0.16

oldown

0.16

/build

0.16

allen

0.16

/lic

0.15

squ

0.15

Activations Density 0.032%

references to actions related to purchasing and acquiring items

No Comments

No Known Activations