INDEX

Explanations

structure and syntax elements in code or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

abez

-0.15

horn

-0.15

bben

-0.14

usz

-0.14

Ø®Ø´

-0.14

evt

-0.14

rum

-0.14

á»įng

-0.13

.newBuilder

-0.13

.TextAlignment

-0.13

POSITIVE LOGITS

0.17

 Hairst

0.16

LOC

0.15

ruby

0.15

 Duch

0.15

readcr

0.15

icket

0.14

ierce

0.14

orted

0.14

udit

0.14

Activations Density 0.055%

structure and syntax elements in code or programming

No Comments

No Known Activations