INDEX

Explanations

technical terms and configurations related to software or code assembly

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

_BIND

-0.16

ãĤ¯ãĤ»

-0.15

hone

-0.15

motor

-0.15

utron

-0.14

ongan

-0.14

ACCESS

-0.14

owe

-0.14

apy

-0.14

oze

-0.14

POSITIVE LOGITS

BuildContext

0.17

build

0.16

cxx

0.16

run

0.16

 build

0.16

 BUILD

0.16

 targets

0.16

 project

0.15

 Targets

0.15

Activations Density 0.402%

technical terms and configurations related to software or code assembly

No Comments

No Known Activations