INDEX

Explanations

references to code syntax and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

alles

-0.15

ort

-0.14

orb

-0.14

Shield

-0.14

Hod

-0.13

 Ø¨Ø§Ø¹

-0.13

ÑħÐ¾Ð²

-0.13

iske

-0.13

TextStyle

-0.13

é¬

-0.13

POSITIVE LOGITS

/gtest

0.16

 sublicense

0.15

lyph

0.15

 Woodward

0.15

edad

0.14

iveau

0.14

okino

0.14

inois

0.13

ses

0.13

arus

0.13

Activations Density 0.065%

references to code syntax and programming constructs

No Comments

No Known Activations