INDEX

Explanations

functions and conditional statements related to policy validation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.19

-0.16

.ctx

-0.16

[a

-0.15

[Index

-0.15

[u

-0.15

[k

-0.15

[r

-0.14

,idx

-0.14

POSITIVE LOGITS

.call

0.16

_(

0.16

?(

0.15

 Bless

0.15

ollo

0.15

ipple

0.15

okud

0.14

InParameter

0.14

oud

0.14

Activations Density 0.176%

functions and conditional statements related to policy validation

No Comments

No Known Activations