INDEX

Explanations

mentions of missing persons and related details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

resco

-0.17

ndef

-0.16

roken

-0.15

fl

-0.15

 DeÄŁ

-0.15

ouser

-0.15

ModelError

-0.15

ÏĦÏį

-0.15

(çģ«

-0.15

VERTISE

-0.14

POSITIVE LOGITS

 missing

0.60

 disappearance

0.57

 disappeared

0.56

 disappear

0.52

 Missing

0.51

Missing

0.49

missing

0.48

 vanished

0.48

 disappearing

0.47

 MISSING

0.46

Activations Density 0.150%

mentions of missing persons and related details

No Comments

No Known Activations