INDEX

Explanations

phrases that indicate emphasis or significant change in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

holm

-0.16

presso

-0.16

hol

-0.14

ennes

-0.14

lope

-0.14

 Elis

-0.14

 Margin

-0.14

oro

-0.14

 determinant

-0.14

 Bundle

-0.14

POSITIVE LOGITS

oker

0.18

Ã©m

0.16

ITO

0.15

empl

0.14

Ð´Ñı

0.13

ione

0.13

ÑĤÐ¾ÑĢÐ°

0.13

acer

0.13

FieldType

0.13

urdy

0.13

Activations Density 0.039%

phrases that indicate emphasis or significant change in context

No Comments

No Known Activations