INDEX

Explanations

references to game mechanics and boss encounters

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

áº»

-0.18

 Sight

-0.16

ç«ĭãģ¦

-0.15

 inline

-0.14

iano

-0.14

 sight

-0.14

ãĥ¬ãĤ¹

-0.14

orgen

-0.13

esso

-0.13

andom

-0.13

POSITIVE LOGITS

ikut

0.17

ãĥ¼ãĥľ

0.15

eras

0.14

lef

0.14

ivot

0.14

acob

0.14

stem

0.14

jal

0.14

Hed

0.13

icap

0.13

Activations Density 0.031%

references to game mechanics and boss encounters

No Comments

No Known Activations