INDEX

Explanations

phrases indicating dissatisfaction or critiques of quality in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

SCO

-0.15

USA

-0.14

 gradu

-0.14

 intimately

-0.14

gue

-0.14

anga

-0.14

ffa

-0.14

 equally

-0.13

 correct

-0.13

DT

-0.13

POSITIVE LOGITS

 struct

0.17

 quiet

0.17

Ø¨Ø³

0.16

 peaceful

0.16

 litter

0.16

 unique

0.16

 UNIQUE

0.15

 CLEAN

0.15

 backward

0.15

å¯§

0.15

Activations Density 0.010%

phrases indicating dissatisfaction or critiques of quality in various contexts

No Comments

No Known Activations

phrases indicating dissatisfaction or critiques of quality in various contexts

No Comments

No Known Activations