INDEX

Explanations

capitalization patterns, specifically focused on the term "Col" followed by a number

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

longleftrightarrow

-0.16

asurer

-0.15

allas

-0.15

pecies

-0.14

emes

-0.14

Ø®ÙĬ

-0.14

ienia

-0.14

ete

-0.14

Ð²Ð¾Ð»Ñı

-0.14

dos

-0.14

POSITIVE LOGITS

lected

0.30

col

0.26

oured

0.24

LECT

0.23

Col

0.23

ored

0.23

gate

0.23

ombo

0.23

onna

0.21

ours

0.21

Activations Density 0.016%

capitalization patterns, specifically focused on the term "Col" followed by a number

No Comments

No Known Activations