INDEX

Explanations

the phrase "of" highlighting relational or possessive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ileo

-0.16

 TÆ°

-0.16

urons

-0.16

ples

-0.15

imitives

-0.15

zano

-0.15

Zap

-0.15

zsche

-0.15

-0.14

arkin

-0.14

POSITIVE LOGITS

bish

0.15

uria

0.14

enderit

0.14

èĦ±

0.14

phia

0.14

aden

0.13

_esc

0.13

 disproportion

0.13

 ÐºÑĥ

0.13

åľ°

0.13

Activations Density 0.002%

the phrase "of" highlighting relational or possessive contexts

No Comments

No Known Activations