INDEX

Explanations

actions and effects related to problem-solving and contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

yal

-0.16

áŀ¶

-0.16

å¢ĥ

-0.15

iscard

-0.15

heim

-0.14

reon

-0.14

ALLE

-0.14

 Duch

-0.14

_ISO

-0.14

/WebAPI

-0.14

POSITIVE LOGITS

kus

0.16

mpz

0.15

ecz

0.15

idor

0.15

Adv

0.14

ãĥ³ãĥĪ

0.14

 Barth

0.14

parm

0.14

belt

0.14

LOL

0.14

Activations Density 0.111%

actions and effects related to problem-solving and contributions

No Comments

No Known Activations