INDEX

Explanations

phrases emphasizing subjective opinions and observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

endency

-0.15

umd

-0.15

icl

-0.14

andel

-0.14

unte

-0.14

esel

-0.14

ependency

-0.14

icted

-0.14

ction

-0.14

zano

-0.13

POSITIVE LOGITS

_here

0.15

CUS

0.15

here

0.14

Spo

0.14

ãģĵãģĵ

0.14

ç¬

0.14

ÑĤÐµÑĢÐ½

0.14

Pf

0.14

Activations Density 0.034%

phrases emphasizing subjective opinions and observations

No Comments

No Known Activations