INDEX

Explanations

conditions and checks in programming logic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

orsk

-0.15

 macro

-0.14

Rig

-0.14

ritch

-0.14

kinson

-0.14

oods

-0.13

Kod

-0.13

territ

-0.13

ishi

-0.13

 regards

-0.13

POSITIVE LOGITS

ergus

0.15

ä¿

0.15

 elsewhere

0.14

uster

0.14

inou

0.14

 yoksa

0.14

0.13

guard

0.13

Ð³Ð¸

0.13

Activations Density 0.029%

conditions and checks in programming logic

No Comments

No Known Activations