INDEX

Explanations

instances of the word "Thr" followed by numerical values or related words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

arius

-0.16

uche

-0.14

atis

-0.14

Wunused

-0.14

implify

-0.14

statt

-0.14

chip

-0.13

lady

-0.13

eko

-0.13

ëĿ½

-0.13

POSITIVE LOGITS

aub

0.17

ppard

0.16

odor

0.14

 Plantae

0.14

pek

0.14

ington

0.13

ãģ¾ãģŁ

0.13

-devel

0.13

®

0.13

rop

0.13

Activations Density 0.002%

instances of the word "Thr" followed by numerical values or related words

No Comments

No Known Activations