INDEX

Explanations

references to specific items, instructions, or examples in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 exped

-0.15

 Exped

-0.15

bove

-0.14

ienia

-0.14

ÐµÑĢÑĤÐ°

-0.14

Ð¾ÑĤÐ¸

-0.14

-0.13

Fac

-0.13

owers

-0.13

azar

-0.13

POSITIVE LOGITS

 Wich

0.16

 '../../../../../

0.15

 psych

0.14

 Stokes

0.14

utron

0.14

slashes

0.14

ieme

0.14

CM

0.14

ERO

0.14

ENE

0.14

Activations Density 0.088%

references to specific items, instructions, or examples in a text

No Comments

No Known Activations