INDEX

Explanations

terms related to adjectives and descriptions in a document

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inda

-0.17

-0.16

 Slip

-0.15

 Ð¿Ð»Ð¾Ñī

-0.15

itud

-0.15

iktig

-0.14

ãĥ¬ãĥ³

-0.14

ãĤŃãĥ¥

-0.14

thern

-0.14

.idea

-0.14

POSITIVE LOGITS

 ÐºÐ¾Ð»Ð¸ÑĩÐµÑģÑĤÐ²Ð¾

0.19

 Ð²ÑĢÐµÐ¼Ñı

0.19

 ÐºÐ¾Ð»Ð¸ÑĩÐµ

0.18

 Ð·Ð½Ð°ÑĩÐµÐ½Ð¸Ðµ

0.18

ÏīÎ¼Î±

0.18

atre

0.17

 Ð½Ð°Ð·Ð²Ð°Ð½Ð¸Ðµ

0.17

ÑģÑĤÐ²Ð¾

0.17

 ÑĤÐµÑĩÐµÐ½Ð¸Ðµ

0.17

 Ð»Ð¸ÑĨÐ¾

0.17

Activations Density 0.031%

terms related to adjectives and descriptions in a document

No Comments

No Known Activations