INDEX

Explanations

instances of "that" in different contexts, particularly in relation to personal experiences or revelations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

anton

-0.16

jus

-0.15

pler

-0.14

Mul

-0.14

itrust

-0.14

 ìĿ´ìĸ´

-0.14

ongyang

-0.13

abet

-0.13

ayment

-0.13

IED

-0.13

POSITIVE LOGITS

mint

0.15

Ð¾ÑĤÑĮ

0.15

Ã´i

0.15

owie

0.14

_Anim

0.14

ìĤ¬ëŀĳ

0.14

orse

0.14

ave

0.14

Ã§e

0.14

zcze

0.14

Activations Density 0.139%

instances of "that" in different contexts, particularly in relation to personal experiences or revelations

No Comments

No Known Activations