INDEX

Explanations

instances of knowledge acquisition and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

_STRIP

-0.15

 fork

-0.15

ihan

-0.15

cher

-0.14

haps

-0.14

[]=$

-0.14

 Fork

-0.13

ãĥķãĤ

-0.13

 Templ

-0.13

 noticed

-0.13

POSITIVE LOGITS

inkel

0.17

theid

0.17

ippi

0.17

vas

0.16

jee

0.15

 triang

0.15

esser

0.15

_VOID

0.14

lis

0.13

ipel

0.13

Activations Density 0.122%

instances of knowledge acquisition and understanding

No Comments

No Known Activations