INDEX

Explanations

terms related to economic theories and class dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ÑĪÐºÑĥ

-0.17

inaire

-0.17

ansi

-0.15

Ĭ¶

-0.14

=~

-0.14

nage

-0.14

ÑģÐ¾ÑĤ

-0.14

\param

-0.14

redd

-0.14

Hem

-0.14

POSITIVE LOGITS

0.15

por

0.14

edia

0.14

coholic

0.14

itative

0.14

rig

0.14

inces

0.14

ASF

0.14

 unity

0.14

unity

0.14

Activations Density 0.076%

terms related to economic theories and class dynamics

No Comments

No Known Activations