INDEX

Explanations

references to trustworthiness or reliability

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Newport

-0.14

iki

-0.14

emento

-0.14

ims

-0.14

ertia

-0.14

orget

-0.13

ARGET

-0.13

zem

-0.13

 Blasio

-0.13

 Rencontres

-0.13

POSITIVE LOGITS

 Peaks

0.14

ployment

0.14

vg

0.14

avail

0.14

rena

0.14

quam

0.13

ple

0.13

 awakeFromNib

0.13

-io

0.13

Activations Density 0.005%

references to trustworthiness or reliability

No Comments

No Known Activations