INDEX

Explanations

the word "a" in various contexts, indicating a focus on articles and their usage in sentences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ause

-0.16

oyer

-0.15

ymax

-0.15

¹Ħ

-0.15

PropertyChanged

-0.14

orges

-0.14

Ã¹

-0.14

):?>↵

-0.14

bai

-0.14

dk

-0.14

POSITIVE LOGITS

noon

0.16

essel

0.14

 scal

0.13

dej

0.13

isan

0.13

unic

0.13

Scalars

0.13

 Acid

0.13

 Strait

0.13

rani

0.13

Activations Density 0.050%

the word "a" in various contexts, indicating a focus on articles and their usage in sentences

No Comments

No Known Activations