INDEX

Explanations

technical terms and structures related to programming or data reporting

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

gere

-0.15

Î¸Î¹

-0.15

åĽŀ

-0.14

 stad

-0.14

 Eagle

-0.14

bef

-0.13

RIX

-0.13

_SCL

-0.13

 RequestOptions

-0.13

_TODO

-0.13

POSITIVE LOGITS

oir

0.15

acin

0.14

ozor

0.13

áº¹p

0.13

annie

0.13

[Test

0.13

ãĥĨãĥ«

0.13

ozÃŃ

0.13

ninger

0.13

illian

0.13

Activations Density 0.013%

technical terms and structures related to programming or data reporting

No Comments

No Known Activations