INDEX

Explanations

connections and relationships between various elements or ideas within the text

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

lor

-0.16

engo

-0.15

 Ð±Ð¾ÐºÑĥ

-0.15

ican

-0.14

flat

-0.14

obb

-0.14

 flat

-0.14

odon

-0.14

 mandates

-0.13

-flat

-0.13

POSITIVE LOGITS

DAC

0.16

.scalablytyped

0.15

arel

0.14

rena

0.14

sik

0.13

 ÎĳÏģÏĩ

0.13

 Unary

0.13

èĩ³

0.13

Activations Density 0.769%

connections and relationships between various elements or ideas within the text

No Comments

No Known Activations