INDEX

Explanations

references to automotive generations and models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ster

-0.16

èį£

-0.16

zl

-0.15

otten

-0.15

zza

-0.15

ãĥ©ãĥ¼

-0.15

uster

-0.15

à¸Ĥ

-0.14

ijd

-0.14

 Ø¹Ø²

-0.14

POSITIVE LOGITS

istrat

0.19

 arasÄ±

0.16

oro

0.15

oure

0.15

cig

0.15

holm

0.14

 Harm

0.14

styled

0.14

 Elias

0.14

 harms

0.14

Activations Density 0.055%

references to automotive generations and models

No Comments

No Known Activations