INDEX

Explanations

mentions of code and programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Ð¾Ð»Ð¾Ð¼

-0.15

à¤

-0.15

-0.14

opes

-0.14

ifix

-0.14

 à¸¿

-0.14

perty

-0.14

 Shelf

-0.13

æºĢ

-0.13

ollapse

-0.13

POSITIVE LOGITS

piel

0.17

otos

0.16

andal

0.15

(mi

0.15

Voy

0.15

otas

0.15

atables

0.14

amm

0.14

adera

0.14

ISTR

0.14

Activations Density 0.030%

mentions of code and programming contexts

No Comments

No Known Activations