INDEX

Explanations

references to academic journal volumes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

EMENT

-0.16

eres

-0.16

Ìģt

-0.15

 Ð±ÑĥÐ´ÑĤÐ¾

-0.14

attles

-0.14

åĮº

-0.14

ÅĽcie

-0.14

ainen

-0.14

éĢ

-0.14

ovali

-0.14

POSITIVE LOGITS

StateChanged

0.15

è¿¹

0.15

rap

0.15

ync

0.14

anzi

0.14

esa

0.14

entai

0.13

Cursor

0.13

enk

0.13

decess

0.13

Activations Density 0.003%

references to academic journal volumes

No Comments

No Known Activations