INDEX

Explanations

instances of the pronoun "we" 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

rze

-0.16

gni

-0.15

ieri

-0.15

omo

-0.15

-valu

-0.15

arshal

-0.15

rosso

-0.14

lector

-0.14

 mosaic

-0.14

rippling

-0.14

POSITIVE LOGITS

acer

0.14

Ø·ÙĨ

0.14

jev

0.13

hek

0.13

irting

0.13

ãĤ¡

0.13

 èĹ

0.13

Activations Density 0.055%

instances of the pronoun "we" in various contexts

No Comments

No Known Activations