INDEX

Explanations

references to performance metrics and evaluations

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

_performance

-0.27

 performance

-0.26

performance

-0.24

Performance

-0.23

 performances

-0.23

 Performance

-0.23

 PERFORMANCE

-0.22

æĢ§èĥ½

-0.21

 Perform

-0.20

_perf

-0.20

POSITIVE LOGITS

adox

0.17

razier

0.16

eum

0.16

ces

0.15

/display

0.15

ace

0.15

ptr

0.14

aning

0.14

ances

0.14

Activations Density 0.042%

references to performance metrics and evaluations

No Comments

No Known Activations