INDEX

Explanations

lines or segments of code and configuration elements in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 addslashes

-0.19

lay

-0.17

rients

-0.15

iffin

-0.15

roid

-0.15

bil

-0.15

 pole

-0.15

bard

-0.15

mpl

-0.14

ROID

-0.14

POSITIVE LOGITS

outu

0.15

iteli

0.15

_READONLY

0.14

 Patch

0.14

ationToken

0.14

_CODEC

0.14

 flex

0.14

umper

0.14

_patch

0.14

Patch

0.13

Activations Density 0.000%

lines or segments of code and configuration elements in a programming context

No Comments

No Known Activations