INDEX

Explanations

words associated with specific identifiers or codes, indicating particular items or references

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

BuilderInterface

-0.17

ark

-0.16

arken

-0.15

fts

-0.15

abwe

-0.15

olars

-0.15

 Worst

-0.15

ãĥ©ãĥĥãĤ¯

-0.14

bage

-0.14

etur

-0.14

POSITIVE LOGITS

ÎºÏĮ

0.16

NB

0.15

 Alta

0.14

-Level

0.14

ucky

0.14

 ^{Â°}

0.14

é»ĺ

0.14

Ã©c

0.14

 ë³´ê³ł

0.14

enton

0.14

Activations Density 0.012%

words associated with specific identifiers or codes, indicating particular items or references

No Comments

No Known Activations