INDEX

Explanations

references and citations within academic or technical documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

].[

-0.20

 Pearce

-0.16

-0.15

raison

-0.14

alu

-0.14

isan

-0.14

cta

-0.14

PCS

-0.14

iani

-0.14

 pareja

-0.14

POSITIVE LOGITS

 recently

0.14

oáº¡i

0.14

ArrayOf

0.14

mpr

0.14

 gravid

0.14

merican

0.14

bob

0.14

 where

0.13

USTER

0.13

seealso

0.13

Activations Density 0.057%

references and citations within academic or technical documents

No Comments

No Known Activations