INDEX

Explanations

details related to personal backgrounds and academic achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 representation

-0.16

log

-0.14

arks

-0.14

Ã¤s

-0.13

 opinion

-0.13

 Shaw

-0.13

ocs

-0.13

::=

-0.13

 Implements

-0.13

ood

-0.13

POSITIVE LOGITS

ìĶ

0.16

ARRIER

0.15

Ø²Ø±

0.15

ONTAL

0.15

etooth

0.15

ikip

0.14

imat

0.14

.IsAny

0.14

UCKET

0.14

 Encounter

0.14

Activations Density 0.346%

details related to personal backgrounds and academic achievements

No Comments

No Known Activations