INDEX

Explanations

references to negation or the word "nor"

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

PTH

-0.16

ITTE

-0.16

bak

-0.15

Bak

-0.15

erable

-0.15

bak

-0.15

į

-0.14

ouse

-0.14

Ã¡h

-0.14

ancell

-0.14

POSITIVE LOGITS

icont

0.15

 nail

0.15

 writing

0.15

Cad

0.14

 Dial

0.14

Bre

0.14

Bol

0.14

ancode

0.14

 Lena

0.14

cad

0.13

Activations Density 0.006%

references to negation or the word "nor"

No Comments

No Known Activations