INDEX

Explanations

terms related to architecture and structural elements

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

eyse

-0.16

zell

-0.16

ezier

-0.15

OKIE

-0.15

illance

-0.15

pagen

-0.14

loub

-0.14

getExtension

-0.14

ibri

-0.14

IFn

-0.14

POSITIVE LOGITS

Å¾e

0.16

0.15

zij

0.15

 Zimmer

0.15

Ð»Ð¸Ð¹

0.15

acular

0.14

ãĥ¼ãĥĵ

0.14

Hir

0.14

aching

0.14

Activations Density 0.012%

terms related to architecture and structural elements

No Comments

No Known Activations