INDEX

Explanations

inquiries or discussions regarding opinions or thoughts on specific subjects

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

alleries

-0.15

Deferred

-0.15

doch

-0.14

 Neutral

-0.14

ZE

-0.14

opsis

-0.14

æ³½

-0.14

STONE

-0.14

orest

-0.13

ervas

-0.13

POSITIVE LOGITS

ain

0.20

 mnemonic

0.16

utsch

0.15

rift

0.14

olute

0.14

 uncert

0.14

RFC

0.14

anka

0.13

ainter

0.13

afia

0.13

Activations Density 0.026%

inquiries or discussions regarding opinions or thoughts on specific subjects

No Comments

No Known Activations