INDEX

Explanations

conjunctions and transitions that connect ideas or statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

arden

-0.15

ucs

-0.15

chts

-0.15

ucker

-0.15

ros

-0.14

ulla

-0.14

.Pow

-0.14

locker

-0.13

ula

-0.13

aca

-0.13

POSITIVE LOGITS

Cay

0.16

 forth

0.15

igi

0.14

ysz

0.14

cum

0.14

zp

0.14

 domic

0.14

 mand

0.13

oty

0.13

Activations Density 0.074%

conjunctions and transitions that connect ideas or statements

No Comments

No Known Activations