INDEX

Explanations

instances of quantitative data or metrics expressed in numerical form

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

uncan

-0.15

 Vital

-0.15

áº¯p

-0.15

ALSE

-0.14

 Covered

-0.14

 Diary

-0.14

urus

-0.14

mans

-0.14

obi

-0.14

æľĪ

-0.13

POSITIVE LOGITS

.scalablytyped

0.19

ennen

0.17

peg

0.16

_:

0.16

iley

0.16

aled

0.15

sted

0.15

Peg

0.15

iled

0.15

 Yani

0.15

Activations Density 0.017%

instances of quantitative data or metrics expressed in numerical form

No Comments

No Known Activations