INDEX

Explanations

elements related to timestamps and categorization of content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ongan

-0.19

iram

-0.17

 Gardens

-0.17

rlen

-0.16

flare

-0.15

ulet

-0.15

uko

-0.14

Ð¶Ñĥ

-0.14

inho

-0.14

idan

-0.14

POSITIVE LOGITS

rig

0.17

arty

0.15

 into

0.14

poi

0.14

 cand

0.14

yang

0.14

 permanently

0.13

uppe

0.13

 water

0.13

fil

0.13

Activations Density 0.012%

elements related to timestamps and categorization of content

No Comments

No Known Activations