INDEX

Explanations

phrases that quantify or express a point of view about minimum standards or reliability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

usta

-0.16

zas

-0.15

olls

-0.15

çļĦæĺ¯

-0.15

rou

-0.15

 Lilly

-0.15

isci

-0.15

Zah

-0.14

elize

-0.14

pto

-0.14

POSITIVE LOGITS

èĩ³å°ĳ

0.46

 minimum

0.43

 atleast

0.40

 least

0.35

minimum

0.35

Minimum

0.33

 Minimum

0.33

 alespoÅĪ

0.31

 Least

0.30

 ØŃØ¯Ø§ÙĤÙĦ

0.30

Activations Density 0.092%

phrases that quantify or express a point of view about minimum standards or reliability

No Comments

No Known Activations