INDEX

Explanations

references to specific organizations or initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Ð°ÑĢÑĩ

-0.15

illet

-0.14

AREST

-0.14

ØªØ²

-0.14

_protocol

-0.14

Ã¡cil

-0.13

bler

-0.13

 Vert

-0.13

ONTAL

-0.13

enberg

-0.13

POSITIVE LOGITS

aal

0.16

oref

0.15

ynes

0.15

Ing

0.15

 UObject

0.14

ail

0.14

ercial

0.14

itate

0.14

avanaugh

0.14

'gc

0.14

Activations Density 0.089%

references to specific organizations or initiatives

No Comments

No Known Activations