INDEX

Explanations

terms related to specialized knowledge or expertise in various fields

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

ÑģÑĤÐ°

-0.17

INCT

-0.16

 Tenn

-0.16

isel

-0.15

elda

-0.14

IMIT

-0.14

Ð¾Ð´Ð¾

-0.14

kili

-0.14

isen

-0.14

arken

-0.14

POSITIVE LOGITS

carousel

0.15

endon

0.14

åº§

0.14

.SDK

0.14

ÐµÑĢÐ³

0.14

 multic

0.14

atik

0.14

Ø§ÙĬØ´

0.14

val

0.13

Activations Density 0.004%

terms related to specialized knowledge or expertise in various fields

No Comments

No Known Activations