INDEX

Explanations

phrases indicating ongoing actions or states of being related to experience and participation

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

illy

-0.15

Ø¯ÛĮØ¯

-0.15

ulfilled

-0.14

ë²½

-0.14

ãģ«åħ¥

-0.14

erece

-0.14

ãĥ¼ãĥį

-0.14

ilateral

-0.14

:"-"`↵

-0.14

à¥ģà¤µ

-0.14

POSITIVE LOGITS

 since

0.26

since

0.20

 Since

0.19

Since

0.19

ince

0.18

 ÙħÙĨØ°

0.18

assa

0.17

aga

0.16

 seit

0.16

 existence

0.16

Activations Density 0.172%

phrases indicating ongoing actions or states of being related to experience and participation

No Comments

No Known Activations