INDEX

Explanations

locations and specific place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ãĤ«ãĥ¼

-0.17

Ú©Ø§Øª

-0.15

iband

-0.14

 stitching

-0.14

 addCriterion

-0.14

uzzi

-0.14

etag

-0.14

Thi

-0.14

 Leigh

-0.14

ibe

-0.14

POSITIVE LOGITS

0.22

 Samp

0.21

Dup

0.20

 Shall

0.20

ENC

0.20

Sne

0.19

Dup

0.18

Rob

0.17

Pam

0.16

 Bert

0.16

Activations Density 0.012%

locations and specific place names

No Comments

No Known Activations