INDEX

Explanations

occurrences of the token "om" or similar variations indicating a theme related to health conditions

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

Ø§ÙĨ

-0.23

.scalablytyped

-0.17

ench

-0.16

ic

-0.16

æīķ

-0.15

yll

-0.15

enheim

-0.15

éĺµ

-0.15

auf

-0.15

mong

-0.15

POSITIVE LOGITS

otive

0.20

orphism

0.20

orrow

0.20

ycin

0.19

ar

0.19

orph

0.19

obile

0.18

inee

0.18

be

0.18

Ã¨tre

0.18

Activations Density 0.052%

occurrences of the token "om" or similar variations indicating a theme related to health conditions

No Comments

No Known Activations