INDEX

Explanations

programming concepts and structures related to loops and randomization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Essence

-0.14

Eug

-0.14

 Mixed

-0.14

 Picker

-0.13

bru

-0.13

Ð½ÐµÐ½

-0.13

bir

-0.13

pector

-0.13

ts

-0.13

Ð±Ð¾

-0.13

POSITIVE LOGITS

iÃ£o

0.15

icie

0.14

 tÃ½

0.14

 "...

0.14

 succession

0.14

 hrom

0.14

ossal

0.14

strcasecmp

0.13

oko

0.13

Activations Density 0.084%

programming concepts and structures related to loops and randomization

No Comments

No Known Activations