INDEX

Explanations

expressions of personal reflections and insights

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

 many

-0.16

perhaps

-0.15

 perhaps

-0.15

 while

-0.15

Perhaps

-0.15

_DECLARE

-0.15

 Perhaps

-0.14

 prec

-0.14

 dear

-0.14

plete

-0.14

POSITIVE LOGITS

 especially

0.20

 obviously

0.20

 anytime

0.19

especially

0.19

 Especially

0.17

pecially

0.16

 Guys

0.16

_again

0.15

 Obviously

0.15

Nah

0.15

Activations Density 0.111%

expressions of personal reflections and insights

No Comments

No Known Activations