INDEX

Explanations

mathematical expressions and proofs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

.Tables

-0.15

ARIABLE

-0.14

GORITH

-0.14

GORITHM

-0.13

.asList

-0.13

 kodu

-0.13

BackColor

-0.13

neas

-0.13

TableCell

-0.12

 kino

-0.12

POSITIVE LOGITS

$\

0.21

$I

0.20

$f

0.20

Proof

0.20

 Proof

0.19

 hint

0.19

 edit

0.19

$$

0.19

 edited

0.19

Attempt

0.19

Activations Density 0.113%

mathematical expressions and proofs

No Comments

No Known Activations