INDEX

Explanations

occurrences of the word "two"

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

egers

-0.20

ulumi

-0.16

 sublist

-0.16

eba

-0.15

apollo

-0.15

eger

-0.15

aal

-0.15

AndView

-0.14

StackNavigator

-0.14

 itself

-0.14

POSITIVE LOGITS

áº¡p

0.17

linger

0.15

ffi

0.15

standing

0.14

pie

0.14

Zuk

0.14

ivers

0.14

jes

0.13

aphael

0.13

ieber

0.13

Activations Density 0.021%

occurrences of the word "two"

No Comments

No Known Activations