INDEX

Explanations

references to collective experiences or shared knowledge

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ãĥ¼ãĥģ

-0.16

igr

-0.15

etti

-0.15

utes

-0.14

ighth

-0.14

idon

-0.14

rees

-0.13

VM

-0.13

(es

-0.13

udi

-0.13

POSITIVE LOGITS

 reminded

0.17

 remind

0.16

 awareness

0.15

 speak

0.15

rop

0.15

 parl

0.15

 aware

0.14

OfString

0.14

aware

0.14

 Cass

0.14

Activations Density 0.031%

references to collective experiences or shared knowledge

No Comments

No Known Activations