INDEX

Explanations

references to geographical locations and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ools

-0.16

Ã³ng

-0.15

-0.14

ymes

-0.14

 Kota

-0.13

ooled

-0.13

CEF

-0.13

Ãºb

-0.13

abit

-0.13

POSITIVE LOGITS

oku

0.15

ÅĻev

0.15

Ä±rak

0.14

.Compose

0.14

mol

0.14

::$_

0.14

olla

0.14

strand

0.14

::_

0.14

.Strict

0.14

Activations Density 0.308%

references to geographical locations and events

No Comments

No Known Activations