INDEX

Explanations

specific programming syntax elements and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

arz

-0.16

edia

-0.15

irc

-0.14

ÙĦØª

-0.14

ÑĢÑĥÐ¶

-0.13

reh

-0.13

vel

-0.13

/sdk

-0.13

IXEL

-0.13

cia

-0.13

POSITIVE LOGITS

abe

0.19

trap

0.15

ï»¿↵↵

0.15

Wu

0.15

uem

0.14

combe

0.14

iaux

0.14

 traps

0.14

Hob

0.14

Activations Density 0.007%

specific programming syntax elements and related terminology

No Comments

No Known Activations