INDEX

Explanations

temporal references related to duration or time spent in various roles or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ilis

-0.17

inz

-0.16

addon

-0.16

ellas

-0.15

ewan

-0.15

ÙĦÙħØ§ÙĨ

-0.14

Ð¸Ð½Ð¾Ð²

-0.14

nk

-0.14

ãĥ¼ãĥŀ

-0.14

Timeline

-0.14

POSITIVE LOGITS

 kolo

0.15

ncia

0.15

eners

0.14

 luyá»ĩn

0.14

poon

0.14

ackers

0.14

 sugar

0.14

ÑĤÑİ

0.14

TERN

0.14

ICC

0.14

Activations Density 0.047%

temporal references related to duration or time spent in various roles or experiences

No Comments

No Known Activations