INDEX

Explanations

references to podcasting and related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.19

 Paran

-0.16

×Ļ

-0.16

ading

-0.15

 cháº¿

-0.15

ParameterValue

-0.15

pile

-0.14

ãĥĹãĥ©

-0.14

ãģ®ãģ¯

-0.14

.pet

-0.14

POSITIVE LOGITS

rack

0.19

imoto

0.18

dyn

0.17

fak

0.16

èĬ

0.16

çĽ®çļĦ

0.16

åŃ

0.16

Ð¾Ð´Ñĭ

0.16

ODULE

0.15

abant

0.15

Activations Density 0.089%

references to podcasting and related content

No Comments

No Known Activations