INDEX

Explanations

technical functions and methods related to programming and data manipulation

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

efa

-0.18

eh

-0.17

oÅ¾

-0.16

dna

-0.16

uft

-0.16

pedia

-0.16

ãĥ¶

-0.16

acebook

-0.15

atron

-0.15

arme

-0.15

POSITIVE LOGITS

 Lars

0.16

®

0.15

lesen

0.15

 designated

0.14

 Garr

0.14

Ð¼Ð¾Ð²

0.14

uisse

0.14

pm

0.14

ary

0.13

smith

0.13

Activations Density 0.127%

technical functions and methods related to programming and data manipulation

No Comments

No Known Activations