INDEX

Explanations

references to workers and discussions about their conditions or roles

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

INO

-0.15

ëģĶ

-0.14

aggio

-0.14

DataReader

-0.14

Ù

-0.14

daemon

-0.14

.tight

-0.14

 Clarkson

-0.14

hton

-0.14

icast

-0.13

POSITIVE LOGITS

omite

0.17

uder

0.15

renders

0.15

/Page

0.14

ock

0.14

afari

0.14

Kum

0.14

iry

0.14

-reference

0.14

Ca

0.13

Activations Density 0.008%

references to workers and discussions about their conditions or roles

No Comments

No Known Activations