INDEX

Explanations

specific geographical locations and features related to trails and waterways

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.16

qus

-0.16

Latch

-0.15

 towers

-0.14

 Towers

-0.14

_eof

-0.14

okens

-0.14

Tower

-0.14

agus

-0.14

legate

-0.14

POSITIVE LOGITS

éĢ¸

0.16

akk

0.14

lights

0.14

 Mixed

0.14

OfWork

0.14

 Hakk

0.14

MIX

0.14

/we

0.13

chu

0.13

erves

0.13

Activations Density 1.490%

specific geographical locations and features related to trails and waterways

No Known Activations