INDEX

Explanations

names of educational institutions and academia-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

osta

-0.16

oni

-0.16

á»©

-0.15

ondo

-0.15

amat

-0.14

Ãłi

-0.14

_general

-0.14

chy

-0.13

its

-0.13

ucu

-0.13

POSITIVE LOGITS

ekler

0.16

0.15

_ke

0.14

reira

0.14

0.13

 Ä°ngilizce

0.13

ÏĥÏĦÏģÎ¿

0.13

ARGS

0.13

Activations Density 0.049%

names of educational institutions and academia-related terms

No Comments

No Known Activations

names of educational institutions and academia-related terms

No Comments

No Known Activations