INDEX

Explanations

author names in a structured reference format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

STM

-0.15

arer

-0.15

ook

-0.14

rray

-0.14

bor

-0.14

SqlParameter

-0.14

bay

-0.14

ãģıãģł

-0.14

 Sala

-0.14

ØµØ±

-0.14

POSITIVE LOGITS

eyJ

0.14

Fol

0.14

ully

0.14

 Fusion

0.14

Ø±Ùĥ

0.14

 Beat

0.13

WebRequest

0.13

boom

0.13

utions

0.13

 beat

0.13

Activations Density 0.001%

author names in a structured reference format

No Comments

No Known Activations