INDEX

Explanations

legal disclaimers and liability statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.15

orch

-0.15

 kennenlernen

-0.15

-0.14

ictions

-0.14

eyim

-0.14

aper

-0.14

POSITIVE LOGITS

uppe

0.16

Ø´Ùħ

0.15

'gc

0.15

 Ø³ÙĪØ¯

0.15

ÏĦÏģÎ¿

0.14

 Ambient

0.14

estead

0.14

 Roose

0.14

 Quest

0.14

éł

0.13

Activations Density 0.024%

legal disclaimers and liability statements

No Comments

No Known Activations