INDEX

Explanations

phrases indicating decision-making processes or collaborative actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

klady

-0.15

-0.14

CellStyle

-0.14

UNUSED

-0.14

TickCount

-0.14

onical

-0.13

OrNil

-0.13

 Ø§ÙĦØªÙĪ

-0.13

peÄį

-0.13

OperationException

-0.13

POSITIVE LOGITS

let

1.15

 lets

1.02

let

0.92

Let

0.91

LET

0.81

 Lets

0.81

Let

0.81

lets

0.78

let

0.77

(let

0.71

Activations Density 0.406%

phrases indicating decision-making processes or collaborative actions

No Comments

No Known Activations