INDEX

Explanations

different versions or adaptations of creative works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Braun

-0.17

getMock

-0.15

ÑĢÑİ

-0.15

lsa

-0.15

resa

-0.14

undy

-0.14

cmp

-0.13

ģµ

-0.13

BA

-0.13

iming

-0.13

POSITIVE LOGITS

ross

0.16

ounter

0.15

erb

0.15

<'

0.14

 sorts

0.14

ort

0.13

adr

0.13

 å»

0.13

ulative

0.13

Fur

0.13

Activations Density 0.086%

different versions or adaptations of creative works

No Comments

No Known Activations