INDEX

Explanations

references to locations and geographical entities

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

="__

-0.17

åħ¥åı£

-0.16

ÎµÎ¹Î¿

-0.15

 tá»¥

-0.14

åħ¥ãĤĬ

-0.14

iy

-0.14

entry

-0.14

POSITIVE LOGITS

 send

0.17

æĭ³

0.17

Transfer

0.17

 Transfer

0.17

 source

0.16

 sending

0.16

 transfer

0.16

 export

0.16

send

0.16

 transfers

0.16

Activations Density 0.334%

references to locations and geographical entities

No Comments

No Known Activations