INDEX

Explanations

references to feedback in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 bÃ²

-0.17

ktop

-0.16

-depth

-0.15

esub

-0.14

ERRU

-0.14

ogl

-0.13

ampion

-0.13

è½

-0.13

isce

-0.13

expo

-0.13

POSITIVE LOGITS

/Instruction

0.18

aries

0.15

lick

0.15

 ìĤ¬íķŃ

0.15

ivate

0.15

rix

0.15

0.14

Ð¾ÐºÑĥ

0.14

agine

0.14

Activations Density 0.013%

references to feedback in various contexts

No Comments

No Known Activations