INDEX

Explanations

frequent and diverse connecting words and phrases within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ourcem

-0.15

illas

-0.15

 Fairfax

-0.15

cul

-0.15

tuk

-0.14

boru

-0.14

 Shaun

-0.14

 aggregate

-0.14

rive

-0.13

ards

-0.13

POSITIVE LOGITS

Shares

0.15

.cat

0.15

ucken

0.14

luk

0.14

åĪĴ

0.14

.AD

0.14

 æ¡

0.14

ãĤ¨ãĥ«

0.14

 Sparks

0.14

éĿ

0.14

Activations Density 0.001%

frequent and diverse connecting words and phrases within the text

No Comments

No Known Activations