INDEX

Explanations

instances of time or frequency references in a narrative context

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

jon

-0.15

 Gratuit

-0.15

abet

-0.14

/GPL

-0.14

 Parsons

-0.14

ìŀĦ

-0.14

xx

-0.13

.percent

-0.13

eea

-0.13

Ð¸Ð¼Ñĥ

-0.13

POSITIVE LOGITS

ãĥ¼ãĥĭ

0.17

êµ°

0.14

AAD

0.14

itin

0.14

Ð¾Ð¶

0.14

 addCriterion

0.14

 Consolid

0.14

inite

0.13

 horizontally

0.13

utton

0.13

Activations Density 0.229%

instances of time or frequency references in a narrative context

No Comments

No Known Activations