INDEX

Explanations

references to mistakes or errors in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ovna

-0.15

ITO

-0.15

actors

-0.14

enty

-0.14

 ØªØ²

-0.14

 overpower

-0.14

 disturbing

-0.13

 Durch

-0.13

anvas

-0.13

POSITIVE LOGITS

 cost

0.53

cost

0.49

 Cost

0.47

-cost

0.43

Cost

0.43

 COST

0.42

 costs

0.41

_cost

0.39

 costing

0.38

.cost

0.36

Activations Density 0.254%

references to mistakes or errors in various contexts

No Comments

No Known Activations