INDEX

Explanations

terms related to the process of making or constructing something

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

roi

-0.16

imate

-0.15

dy

-0.15

 Tang

-0.15

ific

-0.15

áº¿n

-0.14

lify

-0.14

dy

-0.14

ol

-0.14

allen

-0.14

POSITIVE LOGITS

_mirror

0.15

apos

0.15

ÃĹ↵↵

0.15

irit

0.15

iÅ¡

0.15

imson

0.14

á»£

0.14

ÛĮØ´ÙĨ

0.14

lub

0.14

 LIABILITY

0.14

Activations Density 0.006%

terms related to the process of making or constructing something

No Comments

No Known Activations