INDEX

Explanations

names and references related to a specific individual or character

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

erli

-0.16

 Ø¹Ø§ÙħØ§

-0.15

ilm

-0.14

Mgr

-0.14

[src

-0.14

ocoa

-0.14

erosis

-0.14

iffs

-0.14

ots

-0.14

iff

-0.13

POSITIVE LOGITS

Ø§Ø¹ÙĬ

0.16

ROC

0.15

dek

0.15

orp

0.15

itti

0.14

utow

0.14

(EFFECT

0.14

Å©

0.14

Ø¹Ø±

0.14

Č↵

0.13

Activations Density 0.009%

names and references related to a specific individual or character

No Comments

No Known Activations