INDEX

Explanations

instances of positive or encouraging phrases related to experiences and activities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orie

-0.17

lio

-0.14

lem

-0.14

ÑĢÑĥÐ±

-0.14

GRES

-0.14

swire

-0.14

@}

-0.14

 LÃª

-0.14

imestep

-0.13

 proprio

-0.13

POSITIVE LOGITS

ï¸ı

0.18

/OR

0.16

oland

0.15

nbsp

0.15

enticated

0.15

quot

0.14

/-

0.14

plu

0.14

/of

0.14

Conclusion

0.14

Activations Density 0.027%

instances of positive or encouraging phrases related to experiences and activities

No Comments

No Known Activations