INDEX

Explanations

terms and phrases related to specific measurements or units in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

READING

-0.16

lÃ¡

-0.16

heap

-0.15

è¾ĳ

-0.15

 predecess

-0.15

ì§ĳ

-0.14

 regulator

-0.14

ance

-0.14

 preced

-0.14

ohon

-0.13

POSITIVE LOGITS

chio

0.15

ruh

0.14

 Myth

0.14

 ArgumentError

0.14

Wah

0.14

ra

0.14

toy

0.14

åĭĻ

0.14

owl

0.13

Activations Density 0.028%

terms and phrases related to specific measurements or units in scientific contexts

No Comments

No Known Activations