INDEX

Explanations

terms related to publishing and media operations

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

leigh

-0.16

ewart

-0.16

urn

-0.15

 Stewart

-0.15

_PA

-0.14

 prere

-0.14

ÎµÎ¹

-0.14

.Sdk

-0.14

programming

-0.14

roy

-0.13

POSITIVE LOGITS

LETTE

0.16

inja

0.16

ael

0.15

inden

0.15

ent

0.15

æĶ

0.14

"text

0.14

ffd

0.14

 thÃłnh

0.14

-CS

0.14

Activations Density 0.394%

terms related to publishing and media operations

No Comments

No Known Activations