INDEX

Explanations

references to guidance or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

.createFrom

-0.18

.ShouldBe

-0.16

nika

-0.15

pte

-0.14

erging

-0.14

anzi

-0.14

jom

-0.14

upa

-0.14

enegro

-0.14

 struct

-0.13

POSITIVE LOGITS

 footsteps

0.20

ableObject

0.15

lim

0.14

Ã³t

0.14

à¹Ģà¸Ħà¸¥

0.14

ÑĤÐ°ÑĢ

0.14

habit

0.14

 ìķĪëĤ´

0.14

mailto

0.14

cope

0.14

Activations Density 0.114%

references to guidance or instructions

No Comments

No Known Activations