INDEX

Explanations

pronouns that refer to groups of people, particularly in relation to actions or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

was

-0.22

(s

-0.18

(es

-0.18

Was

-0.17

 itself

-0.16

Was

-0.15

amp

-0.15

 Ø¨Ø§Ø´Ø¯

-0.14

nbsp

-0.14

[s

-0.13

POSITIVE LOGITS

’re

0.69

're

0.63

’ve

0.52

are

0.52

've

0.51

’ll

0.41

'll

0.39

 aren

0.39

’d

0.35

 were

0.35

Activations Density 0.822%

pronouns that refer to groups of people, particularly in relation to actions or sentiments

No Comments

No Known Activations