INDEX

Explanations

programming-related syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

egan

-0.16

thane

-0.16

croft

-0.15

rror

-0.15

asley

-0.15

orget

-0.15

ergus

-0.14

anko

-0.14

alez

-0.14

lez

-0.14

POSITIVE LOGITS

ãĥĥ

0.18

Ð¾Ð²Ð°ÑĢ

0.15

utorial

0.14

ÑģÐ¸

0.14

CORE

0.14

oker

0.14

zon

0.14

bru

0.14

ernel

0.14

.ribbon

0.13

Activations Density 0.159%

programming-related syntax

No Comments

No Known Activations