INDEX

Explanations

references to programming functions and commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

aggable

-0.15

raman

-0.15

edy

-0.15

ovÄĽ

-0.14

webtoken

-0.14

ToWorld

-0.14

feito

-0.14

avit

-0.14

ologue

-0.14

agraph

-0.13

POSITIVE LOGITS

oci

0.16

_merged

0.14

ãĥ¼ãĥģ

0.14

assic

0.14

 nulla

0.14

illac

0.13

ìĤ¬íļĮ

0.13

rab

0.13

 Trot

0.13

Activations Density 0.082%

references to programming functions and commands

No Comments

No Known Activations