INDEX

Explanations

references to academic journal articles or publications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

rance

-0.16

oria

-0.15

gio

-0.15

favor

-0.14

semblies

-0.14

áºŃp

-0.14

retched

-0.14

istic

-0.14

apol

-0.13

rence

-0.13

POSITIVE LOGITS

alars

0.16

oles

0.16

á»¹

0.15

er

0.15

ãĥĲãĥ¼

0.15

ATUS

0.15

/ref

0.14

pha

0.14

à¸²à¸Īà¸²à¸ģ

0.14

uble

0.14

Activations Density 0.003%

references to academic journal articles or publications

No Comments

No Known Activations