INDEX

Explanations

mentions of vehicle models and their model years

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

.scalablytyped

-0.17

angen

-0.16

çıį

-0.16

ï»¿↵↵

-0.15

wend

-0.15

Ø²Ø§Ùħ

-0.15

 JADX

-0.15

 grips

-0.15

elts

-0.14

 Twice

-0.14

POSITIVE LOGITS

eme

0.15

ime

0.15

egral

0.15

¯

0.15

sv

0.14

 Stern

0.14

 Defaults

0.14

Mus

0.14

Activations Density 0.014%

mentions of vehicle models and their model years

No Comments

No Known Activations