INDEX

Explanations

function definitions and their invocation patterns in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 trust

-0.14

emma

-0.14

ophy

-0.14

shm

-0.13

 Bennett

-0.13

 Huck

-0.13

 shade

-0.13

emm

-0.13

ÐºÑĤÐ¸

-0.13

ador

-0.13

POSITIVE LOGITS

missive

0.15

lus

0.15

-urlencoded

0.15

ej

0.14

-package

0.14

.gf

0.14

lez

0.14

 CASCADE

0.14

wap

0.14

ļ

0.13

Activations Density 0.108%

function definitions and their invocation patterns in code

No Comments

No Known Activations