INDEX

Explanations

references to the concept of "world" 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 @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

å³

-0.16

amaz

-0.16

nio

-0.15

umble

-0.15

etz

-0.15

pole

-0.14

emma

-0.14

punk

-0.14

anges

-0.14

dale

-0.14

POSITIVE LOGITS

ptal

0.15

ORIA

0.15

ÑĢÐ°Ñĩ

0.14

åı°

0.14

_Impl

0.14

 pret

0.14

erged

0.14

ilig

0.14

yst

0.14

trak

0.14

Activations Density 0.058%

references to the concept of "world" in various contexts

No Comments

No Known Activations