INDEX

Explanations

programming-related code and components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ngrx

-0.17

otto

-0.16

addtogroup

-0.16

ÄĽÅĻ

-0.15

anou

-0.15

anship

-0.15

áº¯p

-0.15

elong

-0.15

æł

-0.14

owie

-0.14

POSITIVE LOGITS

0.15

util

0.14

ãĥ¬ãĤ¹

0.14

Inn

0.14

ê¹Į

0.13

INA

0.13

 VerfÃ¼g

0.13

 blessed

0.13

 alert

0.13

Activations Density 0.029%

programming-related code and components

No Comments

No Known Activations