INDEX

Explanations

code comments in programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

lint

-0.14

-yellow

-0.13

MI

-0.13

aln

-0.13

apo

-0.13

.jsoup

-0.13

ìĥģ

-0.12

dsl

-0.12

 Mike

-0.12

ffer

-0.12

POSITIVE LOGITS

0.16

.gwt

0.15

rypt

0.14

PUR

0.14

trieve

0.14

 Ø²ÙħØ§ÙĨÛĮ

0.14

arÄ±m

0.14

aket

0.14

 conc

0.14

Activations Density 0.005%

code comments in programming syntax

No Comments

No Known Activations