INDEX

Explanations

terms related to academic or theoretical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

_tD

-0.15

 æĿ

-0.15

onis

-0.14

«ĺ

-0.14

hton

-0.14

 intox

-0.14

emies

-0.13

¯¼

-0.13

ho

-0.13

Fin

-0.13

POSITIVE LOGITS

&quot

0.18

Ø±ÙĪÛĮ

0.15

&lt

0.15

uae

0.14

otal

0.14

msp

0.14

Nib

0.14

-webpack

0.14

MBED

0.14

Tumblr

0.14

Activations Density 0.013%

terms related to academic or theoretical concepts

No Comments

No Known Activations