INDEX

Explanations

references to biological classifications and scientific terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

tm

-0.16

rocket

-0.15

ibr

-0.15

Br

-0.15

abr

-0.15

-t

-0.14

uno

-0.14

ardon

-0.14

ylan

-0.14

okay

-0.14

POSITIVE LOGITS

-git

0.16

 catal

0.15

col

0.15

irim

0.15

 conc

0.15

iej

0.15

buah

0.14

urator

0.14

kaar

0.14

Activations Density 0.029%

references to biological classifications and scientific terminology

No Comments

No Known Activations