INDEX

Explanations

references to specific historical years, particularly those in the late 1800s

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

%%%%

-0.18

stants

-0.15

(fun

-0.15

EDIA

-0.15

orch

-0.15

ofile

-0.14

OrElse

-0.14

rieb

-0.14

pone

-0.14

íİ¸

-0.14

POSITIVE LOGITS

oste

0.18

ENCIL

0.15

uede

0.15

eners

0.14

ICLES

0.14

ener

0.14

izada

0.13

ennon

0.13

inkel

0.13

reh

0.13

Activations Density 0.005%

references to specific historical years, particularly those in the late 1800s

No Comments

No Known Activations