INDEX

Explanations

terms related to biological classification and taxonomy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

dera

-0.15

azzi

-0.14

alem

-0.14

ivas

-0.14

ucer

-0.14

ypo

-0.14

fq

-0.13

oret

-0.13

adam

-0.13

adb

-0.13

POSITIVE LOGITS

quam

0.17

iba

0.15

,content

0.15

OfString

0.14

IFA

0.14

 KeyEvent

0.13

MainFrame

0.13

ÛĮ

0.13

 Giang

0.13

Activations Density 0.003%

terms related to biological classification and taxonomy

No Comments

No Known Activations