INDEX

Explanations

references to previously mentioned subjects or concepts

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

yat

-0.15

orman

-0.14

¬ģ

-0.14

ÑĢÑĥÐ±

-0.14

ve

-0.14

 Thur

-0.14

 chung

-0.14

yet

-0.14

ivism

-0.13

POSITIVE LOGITS

lek

0.15

dda

0.14

pek

0.14

odyn

0.14

á»Ľ

0.14

Ŀ

0.13

Ø§ÙĦØª

0.13

enor

0.13

oplan

0.13

Activations Density 0.007%

references to previously mentioned subjects or concepts

No Comments

No Known Activations