INDEX

Explanations

statements regarding the ineffectiveness or consequences of actions and policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ypo

-0.16

imas

-0.15

ith

-0.15

arta

-0.14

è§

-0.14

imb

-0.14

ãģ«ãģĭ

-0.14

.transform

-0.14

ider

-0.14

REPORT

-0.14

POSITIVE LOGITS

nodoc

0.17

 unless

0.16

pery

0.15

GIN

0.15

íĭ±

0.15

izio

0.14

nor

0.14

unless

0.14

 actually

0.14

ÐĴÐŀ

0.14

Activations Density 0.263%

statements regarding the ineffectiveness or consequences of actions and policies

No Comments

No Known Activations