INDEX

Explanations

phrases related to taking steps or actions in progression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

yne

-0.16

sein

-0.15

reffen

-0.15

enties

-0.15

anse

-0.15

bons

-0.14

 Holt

-0.14

Vectorizer

-0.14

Î»Î·ÏĤ

-0.13

estate

-0.13

POSITIVE LOGITS

éª

0.19

swith

0.17

chedulers

0.15

chas

0.15

.jquery

0.15

lessly

0.14

à¹Ħà¸«à¸Ļ

0.14

è¸ı

0.14

chen

0.14

Activations Density 0.044%

phrases related to taking steps or actions in progression

No Comments

No Known Activations