INDEX

Explanations

elements related to programming and data processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

enu

-0.14

 Nack

-0.14

omba

-0.13

inte

-0.13

iju

-0.13

ITA

-0.12

 Pers

-0.12

 announc

-0.12

stal

-0.12

POSITIVE LOGITS

 input

1.24

 inputs

1.08

 Input

1.05

input

1.05

-input

0.99

 INPUT

0.97

Input

0.96

_input

0.95

 Inputs

0.93

.input

0.90

Activations Density 0.154%

elements related to programming and data processing

No Comments

No Known Activations