INDEX

Explanations

instances of the word "of" 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

bred

-0.19

 tá»Ń

-0.16

tright

-0.15

 HOLDERS

-0.15

otto

-0.15

antry

-0.15

ÙĬÙģØ©

-0.14

anni

-0.14

ogan

-0.14

[color

-0.14

POSITIVE LOGITS

esson

0.16

0.15

uche

0.15

civ

0.14

ih

0.14

atische

0.14

Ð»ÐµÐ²

0.14

å§Ĩ

0.14

aphore

0.14

çĶº

0.14

Activations Density 0.013%

instances of the word "of" in various contexts

No Comments

No Known Activations