INDEX

Explanations

occurrences of the article "a" and its variants 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 @ 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

 Orth

-0.15

_resize

-0.15

 Greene

-0.14

 Ross

-0.14

inars

-0.14

GLE

-0.14

poÄį

-0.14

 Courtney

-0.13

 womb

-0.13

 Abed

-0.13

POSITIVE LOGITS

Jeg

0.18

anoi

0.17

atoi

0.17

flare

0.17

rella

0.16

odesk

0.16

averse

0.15

@nate

0.15

amburg

0.15

flip

0.15

Activations Density 0.052%

occurrences of the article "a" and its variants in various contexts

No Comments

No Known Activations