INDEX

Explanations

punctuation marks or sentence boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

verts

-0.16

 Cure

-0.14

agle

-0.14

ilot

-0.14

ego

-0.14

 quotas

-0.14

bole

-0.14

ÑģÑĥ

-0.14

orting

-0.14

POSITIVE LOGITS

 sweep

0.16

ãĥĸãĥŃ

0.15

.radioButton

0.15

ansom

0.14

adio

0.14

nest

0.14

uesta

0.14

 Mess

0.13

hape

0.13

Ãłm

0.13

Activations Density 0.015%

punctuation marks or sentence boundaries

No Comments

No Known Activations