INDEX

Explanations

occurrences of the word "pretty" or its variations

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

ped

-0.15

usk

-0.15

uby

-0.15

kit

-0.15

stk

-0.15

pled

-0.15

ew

-0.14

ilog

-0.14

edian

-0.14

sted

-0.14

POSITIVE LOGITS

alley

0.14

Ð»ÑĥÐ±

0.14

 veter

0.14

ollar

0.13

asar

0.13

 attribution

0.13

olley

0.13

ogy

0.13

Toy

0.13

Activations Density 0.011%

occurrences of the word "pretty" or its variations

No Comments

No Known Activations