INDEX

Explanations

references to game shows and competitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

isphere

-0.16

nodoc

-0.16

ilha

-0.16

UBLE

-0.15

woff

-0.15

onor

-0.14

.tpl

-0.14

alto

-0.14

oreach

-0.14

nore

-0.14

POSITIVE LOGITS

 Segment

0.20

 segment

0.18

lat

0.15

SED

0.15

éĢĨ

0.14

NT

0.14

ped

0.14

 solids

0.14

Segment

0.14

Activations Density 0.023%

references to game shows and competitions

No Comments

No Known Activations