INDEX

Explanations

various instances of commas and quotations, indicating a focus on textual punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

utow

-0.17

OTES

-0.16

ekim

-0.16

serter

-0.15

ordes

-0.15

iente

-0.15

OR

-0.15

Jac

-0.14

italic

-0.14

ometr

-0.14

POSITIVE LOGITS

adir

0.19

ib

0.18

 Estr

0.17

ext

0.16

ullo

0.16

Ext

0.16

anza

0.16

 Gang

0.15

Nut

0.15

Pur

0.15

Activations Density 0.034%

various instances of commas and quotations, indicating a focus on textual punctuation

No Comments

No Known Activations