INDEX

Explanations

references to horizontal and vertical alignment or orientation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

enza

-0.20

ãĥ³ãĥĦ

-0.16

 Howe

-0.15

Ã³ÅĤ

-0.14

eva

-0.14

/plugin

-0.14

nown

-0.14

axe

-0.14

enze

-0.14

icio

-0.13

POSITIVE LOGITS

erk

0.16

issent

0.15

iser

0.15

iginal

0.14

asket

0.14

lsru

0.14

seealso

0.13

 stuck

0.13

 justify

0.13

Ã¶k

0.13

Activations Density 0.028%

references to horizontal and vertical alignment or orientation

No Comments

No Known Activations