INDEX

Explanations

specific identifiers related to awards and honors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

-0.16

oll

-0.15

 Garn

-0.14

ong

-0.14

imer

-0.14

Gow

-0.14

-0.13

POSITIVE LOGITS

ULO

0.15

ç·Ĵ

0.15

Ã¼le

0.14

``(

0.14

addle

0.14

 prosec

0.14

enant

0.14

.omg

0.13

Ħä»¶

0.13

à¤¾à¤¯à¤¦

0.13

Activations Density 0.027%

specific identifiers related to awards and honors

No Comments

No Known Activations