INDEX

Explanations

quotation marks indicating direct speech or quotations in text

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

ogi

-0.17

Ã¦

-0.15

Ð°Ð²

-0.14

igu

-0.14

iggins

-0.13

etch

-0.13

 Agencies

-0.13

atri

-0.13

otes

-0.13

dv

-0.13

POSITIVE LOGITS

-lfs

0.14

çĴ

0.13

alth

0.13

sav

0.13

Pil

0.13

.lucene

0.13

ãĥªãĤ«

0.13

é½

0.13

splash

0.12

Activations Density 0.048%

quotation marks indicating direct speech or quotations in text

No Comments

No Known Activations