INDEX

Explanations

references to document-related variables and operations in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ashi

-0.17

 Gauge

-0.17

ure

-0.16

usa

-0.15

mod

-0.14

oad

-0.14

Ã¼re

-0.14

 setup

-0.14

bing

-0.14

POSITIVE LOGITS

.nih

0.15

fir

0.15

ucene

0.15

aft

0.14

gren

0.14

adero

0.14

ifen

0.14

regunta

0.14

:NS

0.14

":""

0.14

Activations Density 0.104%

references to document-related variables and operations in programming contexts

No Comments

No Known Activations