INDEX

Explanations

references to user profiles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Lawson

-0.15

ilm

-0.15

ling

-0.14

 Wass

-0.14

orf

-0.14

oral

-0.14

OP

-0.14

Ø®ÙĦ

-0.14

Explore

-0.14

Jer

-0.14

POSITIVE LOGITS

estone

0.15

Peripheral

0.15

iangle

0.15

andin

0.15

deaux

0.14

bÃŃ

0.14

yectos

0.14

indow

0.14

hq

0.14

ymb

0.14

Activations Density 0.009%

references to user profiles

No Comments

No Known Activations