INDEX

Explanations

mathematical notation and symbols related to equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

rible

-0.17

iddi

-0.15

agram

-0.15

.scalablytyped

-0.15

aeper

-0.14

iali

-0.14

(strpos

-0.14

 crater

-0.13

.Apis

-0.13

 quote

-0.13

POSITIVE LOGITS

|↵

0.26

|.↵

0.25

|.

0.24

|,↵

0.23

|↵↵

0.23

|=

0.21

|=

0.20

|}↵

0.20

|:

0.20

Activations Density 0.036%

mathematical notation and symbols related to equations

No Comments

No Known Activations