INDEX

Explanations

variations of the word "look" and related expressions of appearance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ctica

-0.16

ula

-0.16

ê·¹

-0.15

mlin

-0.15

_QUOTES

-0.15

uju

-0.14

ulas

-0.14

Ø§Ú¯

-0.14

ad

-0.14

emand

-0.14

POSITIVE LOGITS

 like

0.33

 Like

0.20

 alike

0.20

 exactly

0.20

like

0.19

 LIKE

0.19

Like

0.19

 nhÆ°

0.18

 como

0.18

 comme

0.18

Activations Density 0.060%

variations of the word "look" and related expressions of appearance

No Comments

No Known Activations