INDEX

Explanations

terms related to professional backgrounds and career experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

agrams

-0.14

upp

-0.14

ibs

-0.14

_WM

-0.14

 Railway

-0.13

lobs

-0.13

maal

-0.13

uco

-0.13

ÑĪÐµ

-0.13

atable

-0.13

POSITIVE LOGITS

ARRANT

0.16

à¸Ĭà¸Ļ

0.15

 corrid

0.15

HING

0.15

OPY

0.14

 ë©´

0.14

tember

0.14

Hi

0.14

viron

0.14

 Carlton

0.14

Activations Density 0.259%

terms related to professional backgrounds and career experiences

No Comments

No Known Activations