INDEX

Explanations

phrases related to professional roles and job responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

inges

-0.15

 Bates

-0.15

aN

-0.15

otify

-0.14

regor

-0.13

eller

-0.13

odega

-0.13

_FREQ

-0.13

_MAJOR

-0.13

enen

-0.13

POSITIVE LOGITS

 Hlav

0.17

uracy

0.15

vre

0.15

 Wander

0.15

akh

0.14

us

0.14

ivalence

0.14

ypad

0.14

ReadWrite

0.14

ilere

0.14

Activations Density 0.109%

phrases related to professional roles and job responsibilities

No Comments

No Known Activations