INDEX

Explanations

terms related to abstract ideas and conceptual frameworks

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

DataURL

-0.15

umat

-0.15

getc

-0.15

yles

-0.14

Dub

-0.14

.toObject

-0.14

rouw

-0.14

Ank

-0.14

 Ð²Ð½ÑĥÑĤ

-0.13

rops

-0.13

POSITIVE LOGITS

itter

0.16

gaard

0.15

ache

0.15

gnore

0.14

endon

0.14

ulus

0.14

ion

0.14

gu

0.14

construct

0.14

gel

0.13

Activations Density 0.176%

terms related to abstract ideas and conceptual frameworks

No Comments

No Known Activations