INDEX

Explanations

references to occupational roles and related tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

MN

-0.16

-0.15

ÙĮ

-0.14

holder

-0.14

ij

-0.14

ijn

-0.14

 Beste

-0.14

.Core

-0.14

-0.13

alin

-0.13

POSITIVE LOGITS

 themselves

0.20

ovah

0.18

Ã¶g

0.17

ignon

0.16

zsche

0.16

ickerView

0.16

nicos

0.15

orman

0.15

acier

0.15

PIO

0.15

Activations Density 0.648%

references to occupational roles and related tasks

No Comments

No Known Activations