INDEX

Explanations

references to specific years

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

thouse

-0.15

RTL

-0.14

ensing

-0.14

 reversing

-0.13

Yap

-0.13

eniable

-0.13

ÙħØ´

-0.13

onse

-0.13

 Hale

-0.13

ipl

-0.13

POSITIVE LOGITS

Ð¾ÑĢÐ¾Ð´

0.17

ì¹Ń

0.16

atown

0.15

plib

0.15

antor

0.14

 Colum

0.14

avern

0.14

ThanOr

0.14

alar

0.14

zag

0.14

Activations Density 0.001%

references to specific years

No Comments

No Known Activations