INDEX

Explanations

phrases that indicate capability or the potential to perform an action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 becoming

-0.15

èĥ½å¤Ł

-0.14

 Likely

-0.14

hta

-0.14

ikal

-0.14

verts

-0.14

 Allow

-0.13

ãĤ¤ãĥ³ãĥĪ

-0.13

 likely

-0.13

yr

-0.13

POSITIVE LOGITS

-bodied

0.25

/disable

0.18

berra

0.17

ister

0.17

 easily

0.16

asty

0.16

bod

0.16

ISTER

0.15

ipar

0.15

oire

0.14

Activations Density 0.048%

phrases that indicate capability or the potential to perform an action

No Comments

No Known Activations