INDEX

Explanations

present tense verbs indicating ongoing activities or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iola

-0.16

nze

-0.15

rello

-0.15

ette

-0.14

aginator

-0.14

oÅ¾

-0.14

ado

-0.14

ADO

-0.14

yster

-0.14

eder

-0.14

POSITIVE LOGITS

isas

0.16

EDIA

0.16

 èĹ

0.15

dq

0.14

APR

0.14

 Theme

0.14

elix

0.14

ãĥ¼ãĤ¿ãĥ¼

0.14

alian

0.13

cla

0.13

Activations Density 0.037%

present tense verbs indicating ongoing activities or positions

No Comments

No Known Activations