INDEX

Explanations

conjunctions and connecting words that indicate relationships or participation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ologne

-0.18

pha

-0.18

 Petty

-0.15

 ushort

-0.15

ros

-0.14

 Prospect

-0.14

ambi

-0.14

ATO

-0.14

esses

-0.14

olog

-0.13

POSITIVE LOGITS

endon

0.16

ãĥ¼ãĥĵ

0.15

ench

0.15

iÄįka

0.14

iard

0.14

-lat

0.14

hap

0.14

Tot

0.14

enden

0.13

Reverse

0.13

Activations Density 0.013%

conjunctions and connecting words that indicate relationships or participation

No Comments

No Known Activations