INDEX

Explanations

adverbs that indicate emotional or qualitative nuances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

sey

-0.18

sto

-0.18

fully

-0.16

pin

-0.15

stime

-0.15

erialized

-0.15

 Ying

-0.15

lessly

-0.15

sg

-0.15

POSITIVE LOGITS

tics

0.20

referrer

0.18

Ùĩ

0.18

heid

0.15

-speaking

0.15

avage

0.15

referer

0.15

ADB

0.15

áº¿u

0.15

áº¿

0.15

Activations Density 0.603%

adverbs that indicate emotional or qualitative nuances

No Comments

No Known Activations