INDEX

Explanations

occurrences of class definitions and their structure in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Finger

-0.16

jak

-0.15

 Hawk

-0.15

æĬ

-0.14

oste

-0.14

illy

-0.14

Ð¾ÑĢÑĥ

-0.14

Sil

-0.14

ÐµÑĢÐ³

-0.14

arkan

-0.14

POSITIVE LOGITS

ë£Į

0.14

 Dorm

0.13

ftware

0.13

Vtbl

0.13

ilet

0.13

hone

0.13

cps

0.13

uba

0.13

.java

0.13

adece

0.13

Activations Density 0.007%

occurrences of class definitions and their structure in programming code

No Comments

No Known Activations