INDEX

Explanations

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 @ 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

 stick

-0.15

 sticks

-0.14

 knot

-0.14

 Cass

-0.14

 Stick

-0.13

ç§

-0.13

YYS

-0.13

uty

-0.13

_retry

-0.13

Jew

-0.13

POSITIVE LOGITS

ampo

0.18

_UNIX

0.15

vation

0.15

ille

0.15

åıį

0.14

é³

0.14

 POLITICO

0.14

 Ø§ÙģØª

0.14

oland

0.14

zi

0.14

Activations Density 0.011%

the word "of" in various contexts

No Comments

No Known Activations