INDEX

Explanations

code snippets and technical references related to programming and APIs

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

sta

-0.14

utex

-0.14

stan

-0.14

ç´Ģ

-0.14

enk

-0.14

à¤Łà¤¨

-0.14

itÃ¤

-0.13

Rail

-0.13

immel

-0.13

POSITIVE LOGITS

anim

0.17

acles

0.15

glyph

0.14

rending

0.14

à¹īà¸²à¸ĩ

0.13

weigh

0.13

thon

0.13

erset

0.13

 Bergen

0.12

ç«ľ

0.12

Activations Density 0.007%

code snippets and technical references related to programming and APIs

No Comments

No Known Activations