INDEX

Explanations

concepts related to responsibility and social issues

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

tries

-0.15

 Loose

-0.14

oplast

-0.14

usercontent

-0.14

XA

-0.14

LPARAM

-0.14

 Lookup

-0.13

anta

-0.13

lingen

-0.13

POSITIVE LOGITS

 lies

0.76

lie

0.74

lay

0.63

 Lies

0.54

 lied

0.52

lie

0.52

lies

0.51

 lays

0.49

Lie

0.47

 liegt

0.45

Activations Density 0.331%

concepts related to responsibility and social issues

No Comments

No Known Activations