INDEX

Explanations

instances of complex phrases or structures that convey logical conditions or sequences

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

stoup

-0.16

neau

-0.15

odos

-0.15

ãĥ³ãĥĳ

-0.15

SIGN

-0.14

plash

-0.14

.Logic

-0.14

 tháº§n

-0.14

yna

-0.14

)const

-0.14

POSITIVE LOGITS

yb

0.16

 media

0.15

TAS

0.15

atk

0.14

 setting

0.14

 Chic

0.14

 intimate

0.14

 Marker

0.14

 events

0.14

Rated

0.14

Activations Density 0.003%

instances of complex phrases or structures that convey logical conditions or sequences

No Comments

No Known Activations