INDEX

Explanations

occurrences of the letter "O" 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aho

-0.19

artz

-0.18

utos

-0.16

anel

-0.15

eno

-0.15

thora

-0.14

odable

-0.14

 continuity

-0.14

trag

-0.14

POSITIVE LOGITS

aiser

0.16

Æ°á»Łng

0.15

Projected

0.15

ÙĨØ¹

0.15

uw

0.14

ForObject

0.14

esting

0.14

uld

0.14

EXPECTED

0.14

ogram

0.14

Activations Density 0.022%

occurrences of the letter "O" in various contexts

No Comments

No Known Activations