INDEX

Explanations

references to licensing or regulatory terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

isson

-0.18

inia

-0.16

.fd

-0.15

avou

-0.15

ekt

-0.14

 past

-0.14

 Dahl

-0.14

ITED

-0.14

ÑģÐ¾Ð²

-0.14

radu

-0.13

POSITIVE LOGITS

_MACRO

0.17

ady

0.15

 GOODMAN

0.15

lord

0.15

iec

0.15

urf

0.15

.idea

0.15

hm

0.15

ÃŃnh

0.14

æĿŁ

0.14

Activations Density 0.008%

references to licensing or regulatory terms

No Comments

No Known Activations