INDEX

Explanations

references to procedures and conditions in programming or function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 Sommer

-0.14

Äįer

-0.14

 sensation

-0.14

 corner

-0.14

ninger

-0.14

attention

-0.13

assa

-0.13

edis

-0.13

_protocol

-0.13

arg

-0.13

POSITIVE LOGITS

omite

0.17

ecta

0.15

à¸Ļà¸Ń

0.15

maktan

0.14

ãĥ©ãĤ¯

0.14

zon

0.14

à¸Ļà¸ķ

0.14

 gameTime

0.13

 Buck

0.13

ctic

0.13

Activations Density 0.070%

references to procedures and conditions in programming or function definitions

No Comments

No Known Activations