INDEX

Explanations

references to specific months and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

åħµ

-0.16

-0.15

orman

-0.15

iger

-0.14

 prop

-0.14

ickle

-0.14

inel

-0.14

POSITIVE LOGITS

0.20

PRINTF

0.16

.MixedReality

0.15

uÃ§

0.15

ãĥĪãĥ«

0.15

.latest

0.15

Û²Û°Û²

0.14

ucer

0.14

ellas

0.14

jspx

0.14

Activations Density 0.111%

references to specific months and dates

No Comments

No Known Activations