INDEX

Explanations

references to catalogues or listings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

erais

-0.18

ilan

-0.16

 religion

-0.16

elder

-0.16

oct

-0.14

ema

-0.14

 Binder

-0.14

 sept

-0.14

.xtext

-0.14

 precedent

-0.13

POSITIVE LOGITS

.scalablytyped

0.19

 Truy

0.16

.cx

0.15

ButtonTitles

0.15

SD

0.15

ÑĬ

0.14

anmar

0.14

IDGET

0.14

 RuntimeMethod

0.14

roti

0.14

Activations Density 0.007%

references to catalogues or listings

No Comments

No Known Activations