INDEX

Explanations

connections and associative relationships in textual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ToObject

-0.16

 Dank

-0.16

hir

-0.15

chter

-0.14

trieve

-0.14

ickey

-0.14

rud

-0.14

Lol

-0.13

.VisualBasic

-0.13

yll

-0.13

POSITIVE LOGITS

esan

0.17

 Stocks

0.17

bef

0.15

itore

0.15

oust

0.15

czy

0.15

outer

0.14

afort

0.14

aky

0.14

embre

0.14

Activations Density 0.042%

connections and associative relationships in textual content

No Comments

No Known Activations