INDEX

Explanations

instances of the word "we."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Ã¼ss

-0.16

´

-0.15

cede

-0.15

ctor

-0.15

we

-0.15

col

-0.14

we

-0.14

arken

-0.14

olics

-0.14

ced

-0.14

POSITIVE LOGITS

eview

0.16

linger

0.16

bsite

0.15

esk

0.14

asley

0.14

igel

0.14

ilm

0.14

alth

0.14

esp

0.13

Activations Density 0.125%

instances of the word "we."

No Comments

No Known Activations