INDEX

Explanations

phrases connecting multiple items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ÑĥÑĢÐ°

-0.16

gin

-0.15

_SDK

-0.14

ftar

-0.14

rid

-0.14

 Linh

-0.14

Ø§Ø¯Ø§Øª

-0.14

ail

-0.14

/loose

-0.13

nock

-0.13

POSITIVE LOGITS

rescia

0.15

eah

0.14

rch

0.14

Processor

0.14

avou

0.14

resse

0.13

ivot

0.13

ino

0.13

Activations Density 0.139%

phrases connecting multiple items or concepts

No Comments

No Known Activations