INDEX

Explanations

references to educational policies and background check requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ctica

-0.17

OKIE

-0.17

ille

-0.17

ĥn

-0.16

ileo

-0.15

DBObject

-0.15

_vlog

-0.15

è¬Ŀ

-0.15

á»ĳc

-0.15

liable

-0.15

POSITIVE LOGITS

rum

0.15

Ad

0.15

 followed

0.15

Rum

0.15

ears

0.15

shaw

0.14

ey

0.14

 referee

0.14

 lumin

0.14

Activations Density 0.072%

references to educational policies and background check requirements

No Comments

No Known Activations