INDEX

Explanations

references to geographical locations and routes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

psc

-0.15

GridColumn

-0.15

ilos

-0.15

åĽ

-0.14

ieres

-0.14

 FindObjectOfType

-0.14

ÑģÐ¾Ð»

-0.14

ubi

-0.14

oui

-0.14

edl

-0.14

POSITIVE LOGITS

 concurrency

0.21

enen

0.16

 alignments

0.16

Concurrency

0.15

 concurrent

0.15

 plac

0.15

Fish

0.15

 Fish

0.15

usiness

0.15

wi

0.15

Activations Density 0.061%

references to geographical locations and routes

No Comments

No Known Activations