INDEX

Explanations

words that indicate locations or references to places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

essler

-0.16

omit

-0.15

acco

-0.15

 Pert

-0.15

uki

-0.15

atorio

-0.14

 Hayward

-0.14

Ð´ÐµÐ½

-0.14

 DISCLAIMS

-0.14

ogan

-0.14

POSITIVE LOGITS

 micro

0.17

Alternate

0.15

 Micro

0.15

ig

0.15

 gardens

0.15

 MICRO

0.14

 Larson

0.14

 tvar

0.14

ľ

0.14

iveness

0.14

Activations Density 0.027%

words that indicate locations or references to places

No Comments

No Known Activations