INDEX

Explanations

names and identifiers of organisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

inous

-0.17

ihan

-0.16

aka

-0.16

 Roose

-0.16

hem

-0.15

ijken

-0.15

ilet

-0.14

arket

-0.14

kest

-0.14

ÙĨØ¬

-0.14

POSITIVE LOGITS

hol

0.20

onders

0.19

wet

0.18

 foss

0.18

so

0.17

 takson

0.17

so

0.17

tax

0.16

alia

0.16

+xml

0.16

Activations Density 0.010%

names and identifiers of organisms

No Comments

No Known Activations