INDEX

Explanations

code syntax and structures related to variable declarations and assignments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

phet

-0.16

AGO

-0.15

DSA

-0.14

Ð³ÑĢÐ°

-0.14

ANNEL

-0.14

edb

-0.14

dzi

-0.14

ê²¨

-0.14

 Loot

-0.14

itez

-0.14

POSITIVE LOGITS

ScrollBar

0.14

 Kaplan

0.14

Iv

0.14

icol

0.14

ongan

0.14

 presente

0.14

orama

0.13

landers

0.13

Utt

0.13

ergus

0.13

Activations Density 0.077%

code syntax and structures related to variable declarations and assignments

No Comments

No Known Activations