INDEX

Explanations

numerical data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

issent

-0.18

EDIA

-0.16

oningen

-0.15

leigh

-0.15

rait

-0.15

mars

-0.15

 revers

-0.15

ÑīÐ¸Ð½

-0.15

iew

-0.14

jong

-0.14

POSITIVE LOGITS

 Bark

0.17

Aw

0.15

Jim

0.14

orsk

0.14

Aw

0.14

elo

0.14

 analog

0.14

oras

0.14

dings

0.14

(OS

0.13

Activations Density 0.066%

numerical data and statistics

No Comments

No Known Activations